DeepSeek-V4.1-Flash-1017-GGUF
See Unsloth Dynamic 3.0 GGUFs for our quantization benchmarks. Run on a 128GB+ RAM device for the smallest 1-bit, 3-bit on 256GB or full precision on 320GB. Read Guide To run, please use our llama.cpp PR or the Unsloth Desktop app. Get up to 3x faster inference with Unsloth vs other ngram/CPU/VRAM repos./ </div
Params
763.2 B
Context
—
Downloads 30d
1.1 M
Likes
371
Download history
tracking started — chart appears after 7 days of snapshots (3 recorded)1.1 M 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-UD-IQ1_M-00005-of-00005.gguf | IQ1_M | 110.6 GB | 236.6 GB | ❌ Won’t fit |
| DeepSeek-V4.1-Flash-1017-UD-IQ1_S-00005-of-00005.gguf | IQ1_S | 110.6 GB | 236.6 GB | ❌ Won’t fit |
| DeepSeek-V4.1-Flash-1017-UD-IQ2_XXS-00006-of-00006.gguf | IQ2_XXS | 135.2 GB | 263.7 GB | ❌ Won’t fit |
| DeepSeek-V4.1-Flash-1017-UD-Q2_K_XL-00007-of-00007.gguf | Q2_K_XL | 135.2 GB | 263.7 GB | ❌ Won’t fit |
| DeepSeek-V4.1-Flash-1017-UD-IQ3_S-00008-of-00008.gguf | IQ3_S | 161.3 GB | 292.4 GB | ❌ Won’t fit |
| DeepSeek-V4.1-Flash-1017-UD-IQ3_XXS-00007-of-00007.gguf | IQ3_XXS | 161.3 GB | 292.4 GB | ❌ Won’t fit |
| DeepSeek-V4.1-Flash-1017-UD-Q3_K_XL-00008-of-00008.gguf | Q3_K_XL | 202.8 GB | 338.0 GB | ❌ Won’t fit |
| DeepSeek-V4.1-Flash-1017-UD-Q4_K_XL-00008-of-00009.gguf | Q4_K_XL | 202.8 GB | 338.0 GB | ❌ Won’t fit |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Parameters
- 763.2 B
- Licence
- mit
- First seen on the Hub
- 2026-10-17
- Base model
- DeepSeek-V4.1-Flash-1017
- Training datasets
- undisclosed
- Added to our catalog
- 2026-11-08
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any image-text-to-text model