supergemma4-26b-uncensored-gguf-v2
- a model that feels less censored than stock chat releases - a model that is more capable than the raw base on practical text workloads - a compact local GGUF that still serves quickly on Apple Silicon
Params
—
Context
—
Downloads 30d
301 K
Likes
994
Download history
daily snapshots · 36 days
▲ 73 K in the last 30 days (31.9%)
383 K240 K
Aug 23Sep 2Sep 12Sep 21
383 K177 K
Aug 17Aug 29Sep 10Sep 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 |
|---|---|---|---|---|
| supergemma4-26b-uncensored-fast-v2-Q4_K_M.gguf | Q4_K_M | 16.8 GB | 19.0 GB | ✅ Runs comfortably |
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$ ollama run supergemma4-26b-uncensored-gguf-v2 # pin the quantization explicitly $ ollama run supergemma4-26b-uncensored-gguf-v2-q4_k_m
$ huggingface-cli download Jiunsong/supergemma4-26b-uncensored-gguf-v2-GGUF \
supergemma4-26b-uncensored-fast-v2-Q4_K_M.gguf --local-dir .
$ llama-cli -m supergemma4-26b-uncensored-fast-v2-Q4_K_M.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/supergemma4-26b-uncensored-gguf-v2
{
"hf_id": "Jiunsong/supergemma4-26b-uncensored-gguf-v2",
"params_b": null,
"context_length": null,
"license": { "id": "gemma", "commercial": "conditional" },
"downloads_30d": 300508,
"vram_estimates": [
{ "quant": "Q4_K_M", "gb": 19.0 }
],
"updated_at": "2026-08-17T01:00:34Z"
}
Specifications
- Licence
- gemma
- First seen on the Hub
- 2026-04-11
- Base model
- gemma-4-26B-A4B-it
- Training datasets
- undisclosed
- Added to our catalog
- 2026-08-17
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any text-generation model