mlx-community/gemma-4-31b-it-4bit
MLX Communityhuggingface.co/mlx-community/gemma-4-31b-it-4bit
Updated just now · first seen 11 Sept 2026
model_01M294ZDSW098EFE6MH097TXBB
- Parameters
- 31.3B
- T2 · 41 min ago
- Released
- 2 Apr 2026
- T2 · 3 min ago
- License
- apache-2.0
- T2 · 3 min ago
Specification
- Release date
- 2 Apr 2026
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 min agomedium
- Openness
- open-weights
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 41 min agomedium
- License
- apache-2.0
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 min agomedium
- Architecture
- Gemma4ForConditionalGeneration
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 min agomedium
- Parameters
- 31.3B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 41 min agomedium
- Base model
- google/gemma-4-31B-it
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 min agomedium
- Quantization
- 4bit
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 min agomedium
- Quantization format
- mlx
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 min agomedium
- File size
- 18.4 GB
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 min agomedium
- Hugging Face repo
- mlx-community/gemma-4-31b-it-4bit
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 41 min agomedium
- Pipeline tag
- image-text-to-text
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 41 min agomedium
- Model card
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 41 min agomedium
- Downloads
- 44,458
Source:Hugging Face Hub (public pages, model cards, papers)T2observed just nowmedium
- Likes
- 47
Source:Hugging Face Hub (public pages, model cards, papers)T2observed just nowmedium
- Gated
- No
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 min agomedium
- Is quantized
- Yes
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 min agomedium
- Last modified
- 2026-07-05T23:27:34+00:00
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 41 min agomedium
- Library name
- mlx
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 min agomedium
- License url
- https://ai.google.dev/gemma/docs/gemma_4_license
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 min agomedium
- Downloads all time
- 245,789
Source:Hugging Face Hub (public pages, model cards, papers)T2observed just nowmedium
- Model type
- gemma4
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 min agomedium
- Tags
- mlx, safetensors, gemma4, image-text-to-text, 4-bit
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 min agomedium
- Weights dtype
- BF16, U32
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 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
23
Source tiers
T223
Freshest observation
just now
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 | — | 18.5 GB | Yes |
| AMD Instinct MI325X | 4bit | 256 GB | 18.5 GB | Yes |
| AMD Instinct MI300X | 4bit | 192 GB | 18.5 GB | Yes |
| Apple M2 Ultra | 4bit | — | 18.5 GB | Yes |
| NVIDIA B200 | 4bit | 180 GB | 18.5 GB | Yes |
| NVIDIA H200 | 4bit | 141 GB | 18.5 GB | Yes |
| Apple M1 Ultra | 4bit | — | 18.5 GB | Yes |
| Apple M3 Max | 4bit | — | 18.5 GB | Yes |
| Apple M4 Max | 4bit | — | 18.5 GB | Yes |
| NVIDIA DGX Spark | 4bit | 128 GB | 18.5 GB | Yes |
| Apple M2 Max | 4bit | — | 18.5 GB | Yes |
| NVIDIA A100 80GB | 4bit | 80 GB | 18.5 GB | Yes |
| NVIDIA H100 SXM | 4bit | 80 GB | 18.5 GB | Yes |
| Apple M1 Max | 4bit | — | 18.5 GB | Yes |
| Apple M4 Pro | 4bit | — | 18.5 GB | Yes |
| Apple M3 Pro | 4bit | — | 18.5 GB | Yes |
| Apple M1 Pro | 4bit | — | 18.5 GB | Yes |
| Apple M2 Pro | 4bit | — | 18.5 GB | Yes |
| Apple M4 | 4bit | — | 18.5 GB | Yes |
| NVIDIA GeForce RTX 5090 | 4bit | 32 GB | 18.5 GB | Yes |
| Apple M2 | 4bit | — | 18.5 GB | Yes |
| Apple M3 | 4bit | — | 18.5 GB | Yes |
| NVIDIA GeForce RTX 3090 | 4bit | 24 GB | 18.5 GB | Yes |
| NVIDIA GeForce RTX 4090 | 4bit | 24 GB | 18.5 GB | Yes |
| Apple M1 | 4bit | — | 18.5 GB | No |
Ancestors 2
- Gemma 4 31B31.3B
- gemma-4-31BGoogle
This model
mlx-community/gemma-4-31b-it-4bit
31.3B 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
Release daterelease_date1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 2 Apr 2026 | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Opennessopenness1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| open-weights | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Licenselicense1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| apache-2.0 | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Architecturearchitecture1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| Gemma4ForConditionalGeneration | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Parametersparameter_count1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 31.3B | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Base modelbase_model1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| google/gemma-4-31B-it | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Quantizationquantization1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 4bit | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Quantization formatquant_format1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| mlx | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
File sizefile_size_gb1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 18.4 GB | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Hugging Face repohf_repo1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| mlx-community/gemma-4-31b-it-4bit | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Pipeline tagpipeline_tag1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| image-text-to-text | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Model cardmodel_card_url1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| https://huggingface.co/mlx-community/gemma-4-31b-it-4bit | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Downloadsmetric.downloads1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 44,458 | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Likesmetric.likes1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 47 | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Gatedgated1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| No | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Is quantizedis_quantized1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| Yes | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Last modifiedlast_modified1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 2026-07-05T23:27:34+00:00 | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Library namelibrary_name1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| mlx | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
License urllicense_url1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| https://ai.google.dev/gemma/docs/gemma_4_license | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Downloads all timemetric.downloads_all_time1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 245,789 | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Model typemodel_type1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| gemma4 | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Weights dtypeweights_dtype1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| BF16, U32 | → current | current | 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 →
New model: mlx-community/gemma-4-31b-it-4bit (MLX Community)
huggingface
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/mlx-community/gemma-4-31b-it-4bit | model_page | T2· Quality secondary | just now | 2 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/models?author=mlx-community&p=0&sort=downloads | listing | T2· Quality secondary | 38 min ago | 2 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.