Hardware HardwareSystemActive

MacBook Air (Apple M5)

Apple spec sheet data quality79

Memory: 16–32 GB
Bandwidth: 153 GB/s
TDP: —

Run locally with this device →

Specifications

As published

Every value opens its evidence (source, tier, observed time).

Kind: Source:Apple — Mac tech specsT1observed 11 h agohigh
Kind raw: computer
Spec sheet: apple.com/macbook-air/specs
Source:Apple — Mac tech specsT1observed 11 h agohigh
Memory: Source:Apple — Mac tech specsT1observed 11 h agohigh
Memory type: Source:Apple — Mac tech specsT1observed 11 h agohigh
Product line: Source:Apple — Mac tech specsT1observed 11 h agohigh
Memory bandwidth: Source:Apple — Mac tech specsT1observed 11 h agohigh

What can this run?

Models estimated to fit Estimated

Estimate from each model's parameter count, the chosen quantization and context — never a measurement.

Open in Run locally →

Quantization4bit 8bit fp16

Context8.19K 32.8K 131.1K

Configuration16 GB 24 GB 32 GB

EstimatedAll fit figures are estimates, not measurements.246 of 536 evaluated models fit

Assumptions (7)

Estimated, not measured: weights = parameters × bytes/param × 1.15 runtime overhead (or the observed artifact file size when one is recorded).
bytes/param: 4bit = 0.5, 8bit = 1.0, fp16 = 2.0 (uniform quantization, no per-layer exceptions).
KV cache: 2 × layers × kv_heads × head_dim × 2 bytes × context × batch when the architecture is known; otherwise 0.5 GB per 8 192 tokens (× batch), independent of architecture (GQA/MLA models need less).
A model 'fits' when the estimate is at most the device memory minus 2 GB reserved for the OS and framework.
Mixture-of-experts models are estimated on total parameters (all experts must be resident); active parameters are ignored.
Device memory uses the largest configuration when several are listed (e.g. Apple silicon tiers).
Multi-GPU: device memories are summed; interconnect bandwidth, tensor-parallel replication and pipeline bubbles are not modelled.

This device ships in 3 memory configurations (16 / 24 / 32 GB). Estimates use 24 GB — pick another configuration above. Multiple units: use Run locally (memories are summed; interconnect is not modelled).

Model	Params	Est. memory	Headroom	Fits	Breakdown
chatglm2-6bOpen weightsZ.ai (Zhipu AI)	6B	21.8 GB estimated	+0.2 GB	✓ fits	weights 12.0 GB estimated KV cache 8.00 GB (heuristic) overhead 1.8 GB reserved 2 GB context 131,072 × batch 1
GPT-JT-6B-v1Open weightsTogether AI	6B	21.8 GB estimated	+0.2 GB	✓ fits	weights 12.0 GB estimated KV cache 8.00 GB (heuristic) overhead 1.8 GB reserved 2 GB context 131,072 × batch 1
gpt-j-6bOpen weightsEleutherAI	6B	21.8 GB estimated	+0.2 GB	✓ fits	weights 12.0 GB estimated KV cache 8.00 GB (heuristic) overhead 1.8 GB reserved 2 GB context 131,072 × batch 1
gemma-4-E2B-itOpen weightsGoogle	5.12B	19.8 GB estimated	+2.2 GB	✓ fits	weights 10.3 GB estimated KV cache 8.00 GB (heuristic) overhead 1.5 GB reserved 2 GB context 131,072 × batch 1
Molmo2-4BOpen weightsAllen Institute for AI	4.85B	19.2 GB estimated	+2.8 GB	✓ fits	weights 9.7 GB estimated KV cache 8.00 GB (heuristic) overhead 1.5 GB reserved 2 GB context 131,072 × batch 1
Qianfan-OCROpen weightsBaidu	4.74B	18.9 GB estimated	+3.1 GB	✓ fits	weights 9.5 GB estimated KV cache 8.00 GB (heuristic) overhead 1.4 GB reserved 2 GB context 131,072 × batch 1
Voxtral-Mini-3B-2507Open weightsMistral AI	4.68B	18.8 GB estimated	+3.3 GB	✓ fits	weights 9.3 GB estimated KV cache 8.00 GB (heuristic) overhead 1.4 GB reserved 2 GB context 131,072 × batch 1
Qwen3.5-4BOpen weightsQwen	4.66B	18.7 GB estimated	+3.3 GB	✓ fits	weights 9.3 GB estimated KV cache 8.00 GB (heuristic) overhead 1.4 GB reserved 2 GB context 131,072 × batch 1
Qwen3-VL-4B-InstructOpen weightsQwen	4.44B	18.2 GB estimated	+3.8 GB	✓ fits	weights 8.9 GB estimated KV cache 8.00 GB (heuristic) overhead 1.3 GB reserved 2 GB context 131,072 × batch 1
Voxtral-Mini-4B-Realtime-2602Open weightsMistral AI	4.43B	18.2 GB estimated	+3.8 GB	✓ fits	weights 8.9 GB estimated KV cache 8.00 GB (heuristic) overhead 1.3 GB reserved 2 GB context 131,072 × batch 1
Gemma 3 4Brestricted-weightsGoogle	4.3B	17.9 GB estimated	+4.1 GB	✓ fits	weights 8.6 GB estimated KV cache 8.00 GB (heuristic) overhead 1.3 GB reserved 2 GB context 131,072 × batch 1
Ministral-3-3B-Reasoning-2512Open weightsMistral AI	4.25B	17.8 GB estimated	+4.2 GB	✓ fits	weights 8.5 GB estimated KV cache 8.00 GB (heuristic) overhead 1.3 GB reserved 2 GB context 131,072 × batch 1
Phi-3.5-vision-instructOpen weightsMicrosoft	4.15B	17.5 GB estimated	+4.5 GB	✓ fits	weights 8.3 GB estimated KV cache 8.00 GB (heuristic) overhead 1.2 GB reserved 2 GB context 131,072 × batch 1
instructblip-flan-t5-xlOpen weightsSalesforce	4.02B	17.3 GB estimated	+4.7 GB	✓ fits	weights 8.1 GB estimated KV cache 8.00 GB (heuristic) overhead 1.2 GB reserved 2 GB context 131,072 × batch 1
Qwen3-4BOpen weightsQwen	4.02B	17.3 GB estimated	+4.8 GB	✓ fits	weights 8.0 GB estimated KV cache 8.00 GB (heuristic) overhead 1.2 GB reserved 2 GB context 131,072 × batch 1
pplx-embed-context-v1-4bOpen weightsPerplexity AI	4.02B	17.3 GB estimated	+4.8 GB	✓ fits	weights 8.0 GB estimated KV cache 8.00 GB (heuristic) overhead 1.2 GB reserved 2 GB context 131,072 × batch 1
pplx-embed-v1-4bOpen weightsPerplexity AI	4.02B	17.3 GB estimated	+4.8 GB	✓ fits	weights 8.0 GB estimated KV cache 8.00 GB (heuristic) overhead 1.2 GB reserved 2 GB context 131,072 × batch 1
TRELLIS.2-4BOpen weightsMicrosoft	4B	17.2 GB estimated	+4.8 GB	✓ fits	weights 8.0 GB estimated KV cache 8.00 GB (heuristic) overhead 1.2 GB reserved 2 GB context 131,072 × batch 1
granite-vision-4.1-4bOpen weightsIBM	4B	17.2 GB estimated	+4.8 GB	✓ fits	weights 8.0 GB estimated KV cache 8.00 GB (heuristic) overhead 1.2 GB reserved 2 GB context 131,072 × batch 1
blip2-flan-t5-xlOpen weightsSalesforce	3.94B	17.1 GB estimated	+4.9 GB	✓ fits	weights 7.9 GB estimated KV cache 8.00 GB (heuristic) overhead 1.2 GB reserved 2 GB context 131,072 × batch 1
FLUX.2-klein-base-4BOpen weightsBlack Forest Labs	3.88B	16.9 GB estimated	+5.1 GB	✓ fits	weights 7.8 GB estimated KV cache 8.00 GB (heuristic) overhead 1.2 GB reserved 2 GB context 131,072 × batch 1
FLUX.2-klein-4BOpen weightsBlack Forest Labs	3.88B	16.9 GB estimated	+5.1 GB	✓ fits	weights 7.8 GB estimated KV cache 8.00 GB (heuristic) overhead 1.2 GB reserved 2 GB context 131,072 × batch 1
Cosmos3-EdgeOpen weightsNVIDIA	3.86B	16.9 GB estimated	+5.1 GB	✓ fits	weights 7.7 GB estimated KV cache 8.00 GB (heuristic) overhead 1.2 GB reserved 2 GB context 131,072 × batch 1
Ministral 3 3B 2512Open weightsMistral AI	3.85B	16.9 GB estimated	+5.2 GB	✓ fits	weights 7.7 GB estimated KV cache 8.00 GB (heuristic) overhead 1.1 GB reserved 2 GB context 131,072 × batch 1
CARE-XProprietaryMicrosoft	3.8B	16.7 GB estimated	+5.3 GB	✓ fits	weights 7.6 GB estimated KV cache 8.00 GB (heuristic) overhead 1.1 GB reserved 2 GB context 131,072 × batch 1
3b-de-pretrain-research_releaserestricted-weightsCanopy Labs	3.78B	16.7 GB estimated	+5.3 GB	✓ fits	weights 7.6 GB estimated KV cache 8.00 GB (heuristic) overhead 1.1 GB reserved 2 GB context 131,072 × batch 1
3b-ko-pretrain-research_releaseOpen weightsCanopy Labs	3.78B	16.7 GB estimated	+5.3 GB	✓ fits	weights 7.6 GB estimated KV cache 8.00 GB (heuristic) overhead 1.1 GB reserved 2 GB context 131,072 × batch 1
3b-zh-pretrain-research_releaserestricted-weightsCanopy Labs	3.78B	16.7 GB estimated	+5.3 GB	✓ fits	weights 7.6 GB estimated KV cache 8.00 GB (heuristic) overhead 1.1 GB reserved 2 GB context 131,072 × batch 1
3b-fr-pretrain-research_releaserestricted-weightsCanopy Labs	3.78B	16.7 GB estimated	+5.3 GB	✓ fits	weights 7.6 GB estimated KV cache 8.00 GB (heuristic) overhead 1.1 GB reserved 2 GB context 131,072 × batch 1
3b-es_it-pretrain-research_releaserestricted-weightsCanopy Labs	3.78B	16.7 GB estimated	+5.3 GB	✓ fits	weights 7.6 GB estimated KV cache 8.00 GB (heuristic) overhead 1.1 GB reserved 2 GB context 131,072 × batch 1
3b-hi-pretrain-research_releaserestricted-weightsCanopy Labs	3.78B	16.7 GB estimated	+5.3 GB	✓ fits	weights 7.6 GB estimated KV cache 8.00 GB (heuristic) overhead 1.1 GB reserved 2 GB context 131,072 × batch 1
orpheus-3b-0.1-ftOpen weightsCanopy Labs	3.78B	16.7 GB estimated	+5.3 GB	✓ fits	weights 7.6 GB estimated KV cache 8.00 GB (heuristic) overhead 1.1 GB reserved 2 GB context 131,072 × batch 1
orpheus-3b-0.1-pretrainedOpen weightsCanopy Labs	3.78B	16.7 GB estimated	+5.3 GB	✓ fits	weights 7.6 GB estimated KV cache 8.00 GB (heuristic) overhead 1.1 GB reserved 2 GB context 131,072 × batch 1
blip2-opt-2.7bOpen weightsSalesforce	3.74B	16.6 GB estimated	+5.4 GB	✓ fits	weights 7.5 GB estimated KV cache 8.00 GB (heuristic) overhead 1.1 GB reserved 2 GB context 131,072 × batch 1
Qianfan-VL-3BOpen weightsBaidu	3.71B	16.5 GB estimated	+5.5 GB	✓ fits	weights 7.4 GB estimated KV cache 8.00 GB (heuristic) overhead 1.1 GB reserved 2 GB context 131,072 × batch 1
M1-3BOpen weightsTogether AI	3.45B	15.9 GB estimated	+6.1 GB	✓ fits	weights 6.9 GB estimated KV cache 8.00 GB (heuristic) overhead 1.0 GB reserved 2 GB context 131,072 × batch 1
granite-4.1-3bOpen weightsIBM	3.4B	15.8 GB estimated	+6.2 GB	✓ fits	weights 6.8 GB estimated KV cache 8.00 GB (heuristic) overhead 1.0 GB reserved 2 GB context 131,072 × batch 1
DeepSeek-OCR-2Open weightsDeepSeek	3.39B	15.8 GB estimated	+6.2 GB	✓ fits	weights 6.8 GB estimated KV cache 8.00 GB (heuristic) overhead 1.0 GB reserved 2 GB context 131,072 × batch 1
tiny-aya-globalrestricted-weightsCohere	3.35B	15.7 GB estimated	+6.3 GB	✓ fits	weights 6.7 GB estimated KV cache 8.00 GB (heuristic) overhead 1.0 GB reserved 2 GB context 131,072 × batch 1
tiny-aya-baserestricted-weightsCohere	3.35B	15.7 GB estimated	+6.3 GB	✓ fits	weights 6.7 GB estimated KV cache 8.00 GB (heuristic) overhead 1.0 GB reserved 2 GB context 131,072 × batch 1
DeepSeek-OCROpen weightsDeepSeek	3.34B	15.7 GB estimated	+6.3 GB	✓ fits	weights 6.7 GB estimated KV cache 8.00 GB (heuristic) overhead 1.0 GB reserved 2 GB context 131,072 × batch 1
Unlimited-OCROpen weightsBaidu	3.34B	15.7 GB estimated	+6.3 GB	✓ fits	weights 6.7 GB estimated KV cache 8.00 GB (heuristic) overhead 1.0 GB reserved 2 GB context 131,072 × batch 1
3b-hi-ft-research_releaseOpen weightsCanopy Labs	3.3B	15.6 GB estimated	+6.4 GB	✓ fits	weights 6.6 GB estimated KV cache 8.00 GB (heuristic) overhead 1.0 GB reserved 2 GB context 131,072 × batch 1
3b-fr-ft-research_releaseOpen weightsCanopy Labs	3.3B	15.6 GB estimated	+6.4 GB	✓ fits	weights 6.6 GB estimated KV cache 8.00 GB (heuristic) overhead 1.0 GB reserved 2 GB context 131,072 × batch 1
3b-de-ft-research_releaseOpen weightsCanopy Labs	3.3B	15.6 GB estimated	+6.4 GB	✓ fits	weights 6.6 GB estimated KV cache 8.00 GB (heuristic) overhead 1.0 GB reserved 2 GB context 131,072 × batch 1
3b-es_it-ft-research_releaseOpen weightsCanopy Labs	3.3B	15.6 GB estimated	+6.4 GB	✓ fits	weights 6.6 GB estimated KV cache 8.00 GB (heuristic) overhead 1.0 GB reserved 2 GB context 131,072 × batch 1
3b-ko-ft-research_releaseOpen weightsCanopy Labs	3.3B	15.6 GB estimated	+6.4 GB	✓ fits	weights 6.6 GB estimated KV cache 8.00 GB (heuristic) overhead 1.0 GB reserved 2 GB context 131,072 × batch 1
3b-zh-ft-research_releaseOpen weightsCanopy Labs	3.3B	15.6 GB estimated	+6.4 GB	✓ fits	weights 6.6 GB estimated KV cache 8.00 GB (heuristic) overhead 1.0 GB reserved 2 GB context 131,072 × batch 1
Llama 3.2 3B Instructrestricted-weightsMeta AI	3.21B	15.4 GB estimated	+6.6 GB	✓ fits	weights 6.4 GB estimated KV cache 8.00 GB (heuristic) overhead 1.0 GB reserved 2 GB context 131,072 × batch 1
Llama-3.2-3Brestricted-weightsMeta AI	3.21B	15.4 GB estimated	+6.6 GB	✓ fits	weights 6.4 GB estimated KV cache 8.00 GB (heuristic) overhead 1.0 GB reserved 2 GB context 131,072 × batch 1
AI21-Jamba-Reasoning-3BOpen weightsAI21 Labs	3.2B	15.3 GB estimated	+6.7 GB	✓ fits	weights 6.4 GB estimated KV cache 8.00 GB (heuristic) overhead 1.0 GB reserved 2 GB context 131,072 × batch 1
LFM2.5-VL-3BOpen weightsLiquid AI	3.12B	15.2 GB estimated	+6.8 GB	✓ fits	weights 6.3 GB estimated KV cache 8.00 GB (heuristic) overhead 0.9 GB reserved 2 GB context 131,072 × batch 1
Qwen2.5-3B-InstructOpen weightsQwen	3.09B	15.1 GB estimated	+6.9 GB	✓ fits	weights 6.2 GB estimated KV cache 8.00 GB (heuristic) overhead 0.9 GB reserved 2 GB context 131,072 × batch 1
SmolLM3-3BOpen weightsHugging Face	3.08B	15.1 GB estimated	+6.9 GB	✓ fits	weights 6.2 GB estimated KV cache 8.00 GB (heuristic) overhead 0.9 GB reserved 2 GB context 131,072 × batch 1
SmolLM3-3B-BaseOpen weightsHugging Face	3.08B	15.1 GB estimated	+6.9 GB	✓ fits	weights 6.2 GB estimated KV cache 8.00 GB (heuristic) overhead 0.9 GB reserved 2 GB context 131,072 × batch 1
AI21-Jamba2-3BOpen weightsAI21 Labs	3.03B	15.0 GB estimated	+7.0 GB	✓ fits	weights 6.1 GB estimated KV cache 8.00 GB (heuristic) overhead 0.9 GB reserved 2 GB context 131,072 × batch 1
SeedVR-3BOpen weightsByteDance	3B	14.9 GB estimated	+7.1 GB	✓ fits	weights 6.0 GB estimated KV cache 8.00 GB (heuristic) overhead 0.9 GB reserved 2 GB context 131,072 × batch 1
SeedVR2-3BOpen weightsByteDance	3B	14.9 GB estimated	+7.1 GB	✓ fits	weights 6.0 GB estimated KV cache 8.00 GB (heuristic) overhead 0.9 GB reserved 2 GB context 131,072 × batch 1
RedPajama-INCITE-Instruct-3B-v1Open weightsTogether AI	3B	14.9 GB estimated	+7.1 GB	✓ fits	weights 6.0 GB estimated KV cache 8.00 GB (heuristic) overhead 0.9 GB reserved 2 GB context 131,072 × batch 1
RedPajama-INCITE-Base-3B-v1Open weightsTogether AI	3B	14.9 GB estimated	+7.1 GB	✓ fits	weights 6.0 GB estimated KV cache 8.00 GB (heuristic) overhead 0.9 GB reserved 2 GB context 131,072 × batch 1
RedPajama-INCITE-Chat-3B-v1Open weightsTogether AI	3B	14.9 GB estimated	+7.1 GB	✓ fits	weights 6.0 GB estimated KV cache 8.00 GB (heuristic) overhead 0.9 GB reserved 2 GB context 131,072 × batch 1
granite-vision-3.3-2bOpen weightsIBM	2.98B	14.8 GB estimated	+7.2 GB	✓ fits	weights 6.0 GB estimated KV cache 8.00 GB (heuristic) overhead 0.9 GB reserved 2 GB context 131,072 × batch 1
pythia-2.8bOpen weightsEleutherAI	2.91B	14.7 GB estimated	+7.3 GB	✓ fits	weights 5.8 GB estimated KV cache 8.00 GB (heuristic) overhead 0.9 GB reserved 2 GB context 131,072 × batch 1
stablelm-3b-4e1tOpen weightsStability AI	2.8B	14.4 GB estimated	+7.6 GB	✓ fits	weights 5.6 GB estimated KV cache 8.00 GB (heuristic) overhead 0.8 GB reserved 2 GB context 131,072 × batch 1
phi-2Open weightsMicrosoft	2.78B	14.4 GB estimated	+7.6 GB	✓ fits	weights 5.6 GB estimated KV cache 8.00 GB (heuristic) overhead 0.8 GB reserved 2 GB context 131,072 × batch 1
WeMM-Embedding-2BOpen weightsTencent	2.72B	14.3 GB estimated	+7.7 GB	✓ fits	weights 5.4 GB estimated KV cache 8.00 GB (heuristic) overhead 0.8 GB reserved 2 GB context 131,072 × batch 1
LFM2.5-2.6B (free)Open weightsLiquid AI	2.7B	14.2 GB estimated	+7.8 GB	✓ fits	weights 5.4 GB estimated KV cache 8.00 GB (heuristic) overhead 0.8 GB reserved 2 GB context 131,072 × batch 1
sdxl-turboOpen weightsStability AI	2.57B	13.9 GB estimated	+8.1 GB	✓ fits	weights 5.1 GB estimated KV cache 8.00 GB (heuristic) overhead 0.8 GB reserved 2 GB context 131,072 × batch 1
stable-diffusion-xl-base-1.0restricted-weightsStability AI	2.57B	13.9 GB estimated	+8.1 GB	✓ fits	weights 5.1 GB estimated KV cache 8.00 GB (heuristic) overhead 0.8 GB reserved 2 GB context 131,072 × batch 1
North-Micro-Vision-InstructOpen weightsCohere	2.48B	13.7 GB estimated	+8.3 GB	✓ fits	weights 5.0 GB estimated KV cache 8.00 GB (heuristic) overhead 0.8 GB reserved 2 GB context 131,072 × batch 1
stable-diffusion-3.5-mediumOpen weightsStability AI	2.47B	13.7 GB estimated	+8.3 GB	✓ fits	weights 4.9 GB estimated KV cache 8.00 GB (heuristic) overhead 0.7 GB reserved 2 GB context 131,072 × batch 1
UI-TARS-2B-SFTOpen weightsByteDance	2.44B	13.6 GB estimated	+8.4 GB	✓ fits	weights 4.9 GB estimated KV cache 8.00 GB (heuristic) overhead 0.7 GB reserved 2 GB context 131,072 × batch 1
Cosmos-Reason2-2BOpen weightsNVIDIA	2.44B	13.6 GB estimated	+8.4 GB	✓ fits	weights 4.9 GB estimated KV cache 8.00 GB (heuristic) overhead 0.7 GB reserved 2 GB context 131,072 × batch 1
MiniMax-Music3Open weightsMiniMax	2.43B	13.6 GB estimated	+8.4 GB	✓ fits	weights 4.9 GB estimated KV cache 8.00 GB (heuristic) overhead 0.7 GB reserved 2 GB context 131,072 × batch 1
granite-speech-4.1-2bOpen weightsIBM	2.31B	13.3 GB estimated	+8.7 GB	✓ fits	weights 4.6 GB estimated KV cache 8.00 GB (heuristic) overhead 0.7 GB reserved 2 GB context 131,072 × batch 1
stable-audio-3-mediumOpen weightsStability AI	2.31B	13.3 GB estimated	+8.7 GB	✓ fits	weights 4.6 GB estimated KV cache 8.00 GB (heuristic) overhead 0.7 GB reserved 2 GB context 131,072 × batch 1
stable-diffusion-xl-refiner-1.0restricted-weightsStability AI	2.26B	13.2 GB estimated	+8.8 GB	✓ fits	weights 4.5 GB estimated KV cache 8.00 GB (heuristic) overhead 0.7 GB reserved 2 GB context 131,072 × batch 1
GLM-ASR-Nano-2512Open weightsZ.ai (Zhipu AI)	2.26B	13.2 GB estimated	+8.8 GB	✓ fits	weights 4.5 GB estimated KV cache 8.00 GB (heuristic) overhead 0.7 GB reserved 2 GB context 131,072 × batch 1
granite-speech-4.1-2b-narOpen weightsIBM	2.25B	13.2 GB estimated	+8.8 GB	✓ fits	weights 4.5 GB estimated KV cache 8.00 GB (heuristic) overhead 0.7 GB reserved 2 GB context 131,072 × batch 1
SmolVLM2-2.2B-InstructOpen weightsHugging Face	2.25B	13.2 GB estimated	+8.8 GB	✓ fits	weights 4.5 GB estimated KV cache 8.00 GB (heuristic) overhead 0.7 GB reserved 2 GB context 131,072 × batch 1
SmolVLM-InstructOpen weightsHugging Face	2.25B	13.2 GB estimated	+8.8 GB	✓ fits	weights 4.5 GB estimated KV cache 8.00 GB (heuristic) overhead 0.7 GB reserved 2 GB context 131,072 × batch 1
granite-speech-4.1-2b-plusOpen weightsIBM	2.11B	12.8 GB estimated	+9.2 GB	✓ fits	weights 4.2 GB estimated KV cache 8.00 GB (heuristic) overhead 0.6 GB reserved 2 GB context 131,072 × batch 1
stable-diffusion-3-medium-diffusersOpen weightsStability AI	2.08B	12.8 GB estimated	+9.2 GB	✓ fits	weights 4.2 GB estimated KV cache 8.00 GB (heuristic) overhead 0.6 GB reserved 2 GB context 131,072 × batch 1
cohere-transcribe-arabic-07-2026Open weightsCohere	2.07B	12.8 GB estimated	+9.3 GB	✓ fits	weights 4.1 GB estimated KV cache 8.00 GB (heuristic) overhead 0.6 GB reserved 2 GB context 131,072 × batch 1
cohere-transcribe-03-2026Open sourceCohere	2.07B	12.8 GB estimated	+9.3 GB	✓ fits	weights 4.1 GB estimated KV cache 8.00 GB (heuristic) overhead 0.6 GB reserved 2 GB context 131,072 × batch 1
Hy-MT2-1.8BOpen weightsTencent	2.04B	12.7 GB estimated	+9.3 GB	✓ fits	weights 4.1 GB estimated KV cache 8.00 GB (heuristic) overhead 0.6 GB reserved 2 GB context 131,072 × batch 1
Youtu-LLM-2BOpen weightsTencent	1.96B	12.5 GB estimated	+9.5 GB	✓ fits	weights 3.9 GB estimated KV cache 8.00 GB (heuristic) overhead 0.6 GB reserved 2 GB context 131,072 × batch 1
FastVLM-1.5Brestricted-weightsApple	1.91B	12.4 GB estimated	+9.6 GB	✓ fits	weights 3.8 GB estimated KV cache 8.00 GB (heuristic) overhead 0.6 GB reserved 2 GB context 131,072 × batch 1
internlm2_5-1_8b-chatOpen weightsInternLM (Shanghai AI Laboratory)	1.89B	12.3 GB estimated	+9.7 GB	✓ fits	weights 3.8 GB estimated KV cache 8.00 GB (heuristic) overhead 0.6 GB reserved 2 GB context 131,072 × batch 1
siglip2-giant-opt-patch16-384Open weightsGoogle	1.87B	12.3 GB estimated	+9.7 GB	✓ fits	weights 3.7 GB estimated KV cache 8.00 GB (heuristic) overhead 0.6 GB reserved 2 GB context 131,072 × batch 1
amazon/GPT-OSS-20B-P-EAGLEOpen weightsAmazon Web Services	1.8B	12.1 GB estimated	+9.9 GB	✓ fits	weights 3.6 GB estimated KV cache 8.00 GB (heuristic) overhead 0.5 GB reserved 2 GB context 131,072 × batch 1
DeepSeek-R1-Distill-Qwen-1.5BOpen weightsDeepSeek	1.78B	12.1 GB estimated	+9.9 GB	✓ fits	weights 3.5 GB estimated KV cache 8.00 GB (heuristic) overhead 0.5 GB reserved 2 GB context 131,072 × batch 1
SmolLM-1.7B-InstructOpen weightsHugging Face	1.71B	11.9 GB estimated	+10.1 GB	✓ fits	weights 3.4 GB estimated KV cache 8.00 GB (heuristic) overhead 0.5 GB reserved 2 GB context 131,072 × batch 1
SmolLM-1.7BOpen weightsHugging Face	1.71B	11.9 GB estimated	+10.1 GB	✓ fits	weights 3.4 GB estimated KV cache 8.00 GB (heuristic) overhead 0.5 GB reserved 2 GB context 131,072 × batch 1
SmolLM2-1.7B-InstructOpen weightsHugging Face	1.71B	11.9 GB estimated	+10.1 GB	✓ fits	weights 3.4 GB estimated KV cache 8.00 GB (heuristic) overhead 0.5 GB reserved 2 GB context 131,072 × batch 1
SmolLM2-1.7BOpen weightsHugging Face	1.71B	11.9 GB estimated	+10.1 GB	✓ fits	weights 3.4 GB estimated KV cache 8.00 GB (heuristic) overhead 0.5 GB reserved 2 GB context 131,072 × batch 1
amazon/gpt-oss-120b-p-eagle-long-contextOpen weightsAmazon Web Services	1.7B	11.9 GB estimated	+10.1 GB	✓ fits	weights 3.4 GB estimated KV cache 8.00 GB (heuristic) overhead 0.5 GB reserved 2 GB context 131,072 × batch 1
amazon/gpt-oss-120b-p-eagleOpen weightsAmazon Web Services	1.7B	11.9 GB estimated	+10.1 GB	✓ fits	weights 3.4 GB estimated KV cache 8.00 GB (heuristic) overhead 0.5 GB reserved 2 GB context 131,072 × batch 1
internlm2-1_8b-rewardOpen weightsInternLM (Shanghai AI Laboratory)	1.7B	11.9 GB estimated	+10.1 GB	✓ fits	weights 3.4 GB estimated KV cache 8.00 GB (heuristic) overhead 0.5 GB reserved 2 GB context 131,072 × batch 1
LFM2.5-VL-1.6BOpen weightsLiquid AI	1.6B	11.7 GB estimated	+10.3 GB	✓ fits	weights 3.2 GB estimated KV cache 8.00 GB (heuristic) overhead 0.5 GB reserved 2 GB context 131,072 × batch 1
LFM2-VL-1.6BOpen weightsLiquid AI	1.58B	11.7 GB estimated	+10.3 GB	✓ fits	weights 3.2 GB estimated KV cache 8.00 GB (heuristic) overhead 0.5 GB reserved 2 GB context 131,072 × batch 1
Qwen2.5-1.5B-InstructOpen weightsQwen	1.54B	11.6 GB estimated	+10.4 GB	✓ fits	weights 3.1 GB estimated KV cache 8.00 GB (heuristic) overhead 0.5 GB reserved 2 GB context 131,072 × batch 1
WhisperProprietaryOpenAI	1.54B	11.6 GB estimated	+10.4 GB	✓ fits	weights 3.1 GB estimated KV cache 8.00 GB (heuristic) overhead 0.5 GB reserved 2 GB context 131,072 × batch 1
whisper-largeOpen weightsOpenAI	1.54B	11.6 GB estimated	+10.4 GB	✓ fits	weights 3.1 GB estimated KV cache 8.00 GB (heuristic) overhead 0.5 GB reserved 2 GB context 131,072 × batch 1
whisper-large-v2Open weightsOpenAI	1.54B	11.6 GB estimated	+10.4 GB	✓ fits	weights 3.1 GB estimated KV cache 8.00 GB (heuristic) overhead 0.5 GB reserved 2 GB context 131,072 × batch 1
stable-video-diffusion-img2vid-xtOpen weightsStability AI	1.52B	11.5 GB estimated	+10.5 GB	✓ fits	weights 3.0 GB estimated KV cache 8.00 GB (heuristic) overhead 0.5 GB reserved 2 GB context 131,072 × batch 1
stable-video-diffusion-img2vidOpen weightsStability AI	1.52B	11.5 GB estimated	+10.5 GB	✓ fits	weights 3.0 GB estimated KV cache 8.00 GB (heuristic) overhead 0.5 GB reserved 2 GB context 131,072 × batch 1
pythia-1.4bOpen weightsEleutherAI	1.52B	11.5 GB estimated	+10.5 GB	✓ fits	weights 3.0 GB estimated KV cache 8.00 GB (heuristic) overhead 0.5 GB reserved 2 GB context 131,072 × batch 1
OLMo-2-0425-1B-InstructOpen weightsAllen Institute for AI	1.48B	11.4 GB estimated	+10.6 GB	✓ fits	weights 3.0 GB estimated KV cache 8.00 GB (heuristic) overhead 0.5 GB reserved 2 GB context 131,072 × batch 1
OLMo-2-0425-1BOpen weightsAllen Institute for AI	1.48B	11.4 GB estimated	+10.6 GB	✓ fits	weights 3.0 GB estimated KV cache 8.00 GB (heuristic) overhead 0.5 GB reserved 2 GB context 131,072 × batch 1
levanter-backpack-1bOpen weightsStanford CRFM	1.42B	11.3 GB estimated	+10.7 GB	✓ fits	weights 2.8 GB estimated KV cache 8.00 GB (heuristic) overhead 0.4 GB reserved 2 GB context 131,072 × batch 1
privacy-filterOpen weightsOpenAI	1.4B	11.2 GB estimated	+10.8 GB	✓ fits	weights 2.8 GB estimated KV cache 8.00 GB (heuristic) overhead 0.4 GB reserved 2 GB context 131,072 × batch 1
gpt-neo-1.3BOpen weightsEleutherAI	1.37B	11.1 GB estimated	+10.9 GB	✓ fits	weights 2.7 GB estimated KV cache 8.00 GB (heuristic) overhead 0.4 GB reserved 2 GB context 131,072 × batch 1
GLM-OCROpen weightsZ.ai (Zhipu AI)	1.33B	11.1 GB estimated	+10.9 GB	✓ fits	weights 2.6 GB estimated KV cache 8.00 GB (heuristic) overhead 0.4 GB reserved 2 GB context 131,072 × batch 1
nvidia/llama-nemotron-rerank-1b-v2Open weightsNVIDIA	1.24B	10.8 GB estimated	+11.2 GB	✓ fits	weights 2.5 GB estimated KV cache 8.00 GB (heuristic) overhead 0.4 GB reserved 2 GB context 131,072 × batch 1
NousResearch/Llama-3.2-1Brestricted-weightsNous Research	1.24B	10.8 GB estimated	+11.2 GB	✓ fits	weights 2.5 GB estimated KV cache 8.00 GB (heuristic) overhead 0.4 GB reserved 2 GB context 131,072 × batch 1
Llama 3.2 1B Instructrestricted-weightsMeta AI	1.24B	10.8 GB estimated	+11.2 GB	✓ fits	weights 2.5 GB estimated KV cache 8.00 GB (heuristic) overhead 0.4 GB reserved 2 GB context 131,072 × batch 1
Llama-3.2-1Brestricted-weightsMeta AI	1.24B	10.8 GB estimated	+11.2 GB	✓ fits	weights 2.5 GB estimated KV cache 8.00 GB (heuristic) overhead 0.4 GB reserved 2 GB context 131,072 × batch 1
stable-audio-open-1.0Open weightsStability AI	1.21B	10.8 GB estimated	+11.2 GB	✓ fits	weights 2.4 GB estimated KV cache 8.00 GB (heuristic) overhead 0.4 GB reserved 2 GB context 131,072 × batch 1
OLMo-1B-hfOpen weightsAllen Institute for AI	1.18B	10.7 GB estimated	+11.3 GB	✓ fits	weights 2.4 GB estimated KV cache 8.00 GB (heuristic) overhead 0.3 GB reserved 2 GB context 131,072 × batch 1

First 120 models (fitting first). The full list is in Run locally.

MethodEstimated, not measured: weights = parameters × bytes/param × 1.15 runtime overhead (or the observed artifact file size when one is recorded). /methodology

Relations

In the graph

Explore graph →

Manufactured by: Apple
Uses: Apple M5

Timeline

Events

Full timeline →

No events yet

Events are generated by the change engine when a material property, price or result changes.

Sources

Where these facts come from

Source documents
Source	Document	Type	Tier	Last observed	Snapshots
Apple — Mac tech specs	apple.com/macbook-air/specs	spec_page	T1· Official	11 h ago	1

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.