DeepSeek-V4.1-Flash-1017-Uncensored-GSQ-RCO-GGUF
ISTA-DASLab's GSQ-RCO quantizations of DeepSeek-V4.1-Flash-1017 (763B, 384 experts) with DeepSeek's refusal direction projected out of the dense residual writers — the same edit as AtomicChat/DeepSeek-V4.1-Flash-1017-Uncensored-GGUF, measured on every rung.
Params
763.2 B
Context
—
Downloads 30d
137 K
Likes
405
Download history
tracking started — chart appears after 7 days of snapshots (1 recorded)137 K downloads in the last 30 days
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 |
|---|---|---|---|---|
| DeepSeek-V4.1-Flash-1017-GSQ-RCO-IQ2_XXS-00002-of-00004.gguf | IQ2_XXS | 39.4 GB | 158.3 GB | ❌ Won’t fit |
| DeepSeek-V4.1-Flash-1017-GSQ-RCO-IQ2_XS-00001-of-00004.gguf | IQ2_XS | 39.5 GB | 158.5 GB | ❌ Won’t fit |
| DeepSeek-V4.1-Flash-1017-GSQ-RCO-IQ1_M-00003-of-00004.gguf | IQ1_M | 40.0 GB | 159.0 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$ ollama run deepseek-v4-1-flash-1017-uncensored-gsq-rco-gguf # pin the quantization explicitly $ ollama run deepseek-v4-1-flash-1017-uncensored-gsq-rco-gguf-iq1_m
$ huggingface-cli download AtomicChat/DeepSeek-V4.1-Flash-1017-Uncensored-GSQ-RCO-GGUF-GGUF \
DeepSeek-V4.1-Flash-1017-GSQ-RCO-IQ1_M-00003-of-00004.gguf --local-dir .
$ llama-cli -m DeepSeek-V4.1-Flash-1017-GSQ-RCO-IQ1_M-00003-of-00004.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/deepseek-v4-1-flash-1017-uncensored-gsq-rco-gguf
{
"hf_id": "AtomicChat/DeepSeek-V4.1-Flash-1017-Uncensored-GSQ-RCO-GGUF",
"params_b": 763.21,
"context_length": null,
"license": { "id": "mit", "commercial": "yes" },
"downloads_30d": 137288,
"vram_estimates": [
{ "quant": "IQ1_M", "gb": 159.0 },
{ "quant": "IQ2_XS", "gb": 158.5 }
],
"updated_at": "2026-11-10T01:00:43Z"
}
Specifications
- Parameters
- 763.2 B
- Licence
- mit
- First seen on the Hub
- 2026-10-28
- Base model
- DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF
- Training datasets
- undisclosed
- Added to our catalog
- 2026-11-10
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any text-generation model