gemma-4-31B-it-uncensored
Before After ----------------- Refusals (mlabonne, 100 prompts) 100/100 1/100 effective (5 flagged, 4 refusal-then-comply) Refusals (cross-dataset, 686 prompts) — 22/686 (3.2%) KL Divergence 0 (baseline) 0.124 Quality (harmless response length ratio) 1.0 ~1.01 (no degradation)
Params
32.7 B
Context
—
Downloads 30d
244 K
Likes
32
Download history
daily snapshots · 20 days271 K198 K
Sep 2Sep 8Sep 15Sep 21
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | bf16 | 62.5 GB | 74.2 GB | ❌ Won’t fit |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Run it
copy-paste, exact tags checked against the Hub$ curl -s https://aimodelscomparison.com/api/v1/models/gemma-4-31b-it-uncensored
{
"hf_id": "TrevorJS/gemma-4-31B-it-uncensored",
"params_b": 32.68,
"context_length": null,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 244230,
"vram_estimates": [
{ "quant": "bf16", "gb": 74.2 }
],
"updated_at": "2026-09-02T01:00:35Z"
}
Specifications
- Architecture
- Gemma4ForConditionalGeneration
- Parameters
- 32.7 B
- Tensor type
- BF16
- Licence
- apache-2.0
- First seen on the Hub
- 2026-04-04
- Base model
- gemma-4-31B-it
- Training datasets
- undisclosed
- Added to our catalog
- 2026-09-02
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any text-generation model