mlx-community/Qwen3.8-27B-8bit
Updated 39 min ago · first seen 11 Sept 2026
model_01M294ZDSK5H9PSNBC4AFS93PQ
- Parameters
- 27.4B
- T2 · 1 h ago
- Released
- 14 Aug 2026
- T2 · 41 min ago
- License
- apache-2.0
- T2 · 41 min ago
Specification
- Release date
- 14 Aug 2026
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 41 min agomedium
- Openness
- open-weights
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- License
- apache-2.0
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 41 min agomedium
- Architecture
- Qwen3_5ForConditionalGeneration
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 41 min agomedium
- Parameters
- 27.4B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Base model
- Qwen/Qwen3.8-27B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 41 min agomedium
- Quantization
- 8bit
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 41 min agomedium
- Quantization format
- mlx
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 41 min agomedium
- File size
- 29.5 GB
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 41 min agomedium
- Hugging Face repo
- mlx-community/Qwen3.8-27B-8bit
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Pipeline tag
- image-text-to-text
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Model card
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Downloads
- 60,881
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 39 min agomedium
- Likes
- 58
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 39 min agomedium
- Gated
- No
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 41 min agomedium
- Is quantized
- Yes
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 41 min agomedium
- Last modified
- 2026-08-14T16:16:16+00:00
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Library name
- mlx
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 41 min agomedium
- Downloads all time
- 60,881
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 39 min agomedium
- Model type
- qwen3_5
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 41 min agomedium
- Tags
- mlx, safetensors, qwen3_5, image-text-to-text, 8-bit
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 41 min agomedium
- Weights dtype
- BF16, U32
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 41 min agomedium
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
22
Source tiers
T222
Freshest observation
39 min ago
Conflicts
None
Modalities
Modalities unavailable.
Capabilities
Tool calling
Unavailable
Structured output
Unavailable
Reasoning
Unavailable
Vision
Unavailable
Audio
Unavailable
Fine-tuning available
Unavailable
No capability flags have been observed from a source yet — we do not infer them.
No structured attributes yet.
No benchmark results recorded
Current prices
No current prices recorded
Price history
Memory need = bytes per parameter (4-bit ≈ 0.5 × 1.15 overhead, 8-bit 1.0, fp16 2.0) + a KV-cache allowance. Not a measurement.
| Hardware | Quantization | Memory | Est. need | Fits |
|---|---|---|---|---|
| Apple M3 Ultra | 4bit | — | 16.2 GB | Yes |
| AMD Instinct MI325X | 4bit | 256 GB | 16.2 GB | Yes |
| AMD Instinct MI300X | 4bit | 192 GB | 16.2 GB | Yes |
| Apple M2 Ultra | 4bit | — | 16.2 GB | Yes |
| NVIDIA B200 | 4bit | 180 GB | 16.2 GB | Yes |
| NVIDIA H200 | 4bit | 141 GB | 16.2 GB | Yes |
| Apple M1 Ultra | 4bit | — | 16.2 GB | Yes |
| Apple M3 Max | 4bit | — | 16.2 GB | Yes |
| Apple M4 Max | 4bit | — | 16.2 GB | Yes |
| NVIDIA DGX Spark | 4bit | 128 GB | 16.2 GB | Yes |
| Apple M2 Max | 4bit | — | 16.2 GB | Yes |
| NVIDIA A100 80GB | 4bit | 80 GB | 16.2 GB | Yes |
| NVIDIA H100 SXM | 4bit | 80 GB | 16.2 GB | Yes |
| Apple M1 Max | 4bit | — | 16.2 GB | Yes |
| Apple M4 Pro | 4bit | — | 16.2 GB | Yes |
| Apple M3 Pro | 4bit | — | 16.2 GB | Yes |
| Apple M1 Pro | 4bit | — | 16.2 GB | Yes |
| Apple M2 Pro | 4bit | — | 16.2 GB | Yes |
| Apple M4 | 4bit | — | 16.2 GB | Yes |
| NVIDIA GeForce RTX 5090 | 4bit | 32 GB | 16.2 GB | Yes |
| Apple M2 | 4bit | — | 16.2 GB | Yes |
| Apple M3 | 4bit | — | 16.2 GB | Yes |
| NVIDIA GeForce RTX 3090 | 4bit | 24 GB | 16.2 GB | Yes |
| NVIDIA GeForce RTX 4090 | 4bit | 24 GB | 16.2 GB | Yes |
| Apple M1 | 4bit | — | 16.2 GB | No |
Ancestors 1
- Qwen3.8 27B27.8B
This model
mlx-community/Qwen3.8-27B-8bit
27.4B params
Quantizations 0
None recorded.
Descendants 0
None recorded.
Papers 0
No papers linked yet.
Repositories 0
No repositories linked yet.
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history · Tags
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
New model: mlx-community/Qwen3.8-27B-8bit (MLX Community)
huggingface
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/mlx-community/Qwen3.8-27B-8bit/raw/main/README.md | model_card | T2· Quality secondary | 3 min ago | 1 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/mlx-community/Qwen3.8-27B-8bit | model_page | T2· Quality secondary | 39 min ago | 2 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/models?author=mlx-community&p=0&sort=downloads | listing | T2· Quality secondary | 1 h ago | 2 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.