unsloth/gemma-4-26B-A4B-it-qat-GGUF
Updated 2 h ago · first seen 11 Sept 2026
model_01M2950GW4Z1F8GP1HQGK42T54
- Parameters
- 26B · 4B active
- T2 · 2 h ago
- Released
- 5 Jun 2026
- T2 · 2 h ago
- License
- apache-2.0
- T2 · 2 h ago
Specification
- Release date
- 5 Jun 2026
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Openness
- open-weights
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- License
- apache-2.0
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Architecture
- Gemma4ForConditionalGeneration
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Parameters
- 26B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Active parameters
- 4B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Base model
- google/gemma-4-26B-A4B-it-qat-q4_0-unquantized
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Quantization format
- gguf
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Hugging Face repo
- unsloth/gemma-4-26B-A4B-it-qat-GGUF
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Pipeline tag
- image-text-to-text
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Model card
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Downloads
- 693,402
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Likes
- 412
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Gated
- No
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Is quantized
- Yes
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Last modified
- 2026-07-17T12:43:18+00:00
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Library name
- transformers
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- License url
- https://ai.google.dev/gemma/docs/gemma_4_license
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Downloads all time
- 2,263,777
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Model type
- gemma4
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Tags
- transformers, gguf, gemma4, image-text-to-text, unsloth, gemma, google
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h 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
21
Source tiers
T221
Freshest observation
2 h 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 | — | 15.4 GB | Yes |
| AMD Instinct MI325X | 4bit | 256 GB | 15.4 GB | Yes |
| AMD Instinct MI300X | 4bit | 192 GB | 15.4 GB | Yes |
| Apple M2 Ultra | 4bit | — | 15.4 GB | Yes |
| NVIDIA B200 | 4bit | 180 GB | 15.4 GB | Yes |
| NVIDIA H200 | 4bit | 141 GB | 15.4 GB | Yes |
| Apple M1 Ultra | 4bit | — | 15.4 GB | Yes |
| Apple M3 Max | 4bit | — | 15.4 GB | Yes |
| Apple M4 Max | 4bit | — | 15.4 GB | Yes |
| NVIDIA DGX Spark | 4bit | 128 GB | 15.4 GB | Yes |
| Apple M2 Max | 4bit | — | 15.4 GB | Yes |
| NVIDIA A100 80GB | 4bit | 80 GB | 15.4 GB | Yes |
| NVIDIA H100 SXM | 4bit | 80 GB | 15.4 GB | Yes |
| Apple M1 Max | 4bit | — | 15.4 GB | Yes |
| Apple M4 Pro | 4bit | — | 15.4 GB | Yes |
| Apple M3 Pro | 4bit | — | 15.4 GB | Yes |
| Apple M1 Pro | 4bit | — | 15.4 GB | Yes |
| Apple M2 Pro | 4bit | — | 15.4 GB | Yes |
| Apple M4 | 4bit | — | 15.4 GB | Yes |
| NVIDIA GeForce RTX 5090 | 4bit | 32 GB | 15.4 GB | Yes |
| Apple M2 | 4bit | — | 15.4 GB | Yes |
| Apple M3 | 4bit | — | 15.4 GB | Yes |
| NVIDIA GeForce RTX 3090 | 4bit | 24 GB | 15.4 GB | Yes |
| NVIDIA GeForce RTX 4090 | 4bit | 24 GB | 15.4 GB | Yes |
| Apple M1 | 4bit | — | 15.4 GB | No |
Ancestors 1
This model
unsloth/gemma-4-26B-A4B-it-qat-GGUF
26B 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 · Parameters
Parametersparameter_count4
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 26B | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
| 25.2B | → | superseded | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
| 26B | → | superseded | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
| 25.2B | → | superseded | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
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 →
unsloth/gemma-4-26B-A4B-it-qat-GGUF: parameter count changed from 25233142046 to 26000000000
Parameters25.2B→26BhuggingfaceNew model: unsloth/gemma-4-26B-A4B-it-qat-GGUF (Unsloth)
huggingface
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/unsloth/gemma-4-26B-A4B-it-qat-GGUF | model_page | T2· Quality secondary | 2 h ago | 1 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/models?author=unsloth&p=0&sort=downloads | listing | T2· Quality secondary | 3 h ago | 2 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.