All models › deepseek-ai
DeepSeek-V4.1-Flash-1017
deepseek-ai · on Arena since 17 Oct 2026
Download New · waiting for Arena votes
Arena score—Not voted on Arena yet
Size763.2 B228.1 B active per token (mixture of experts)
4-bit download462 GBweights only, Q4_K_M
Max context1024Ktokens, from the model config
Where to use it for free
- Download and run it at home: official weights · GGUF files for Ollama and LM Studio
New: waiting for Arena votes
Released on 17 Oct 2026. Arena has not voted on this model yet. As soon as it does, the model moves into the ranking automatically, usually the next night. Until then you can still check its size, memory needs and speed below.
Speed on popular hardware
| Hardware | GPU memory | Fits? | Speed |
|---|---|---|---|
| RTX 3060 12 GB | 12 GB | Does not fit | — |
| RTX 4060 Ti 16 GB | 16 GB | Does not fit | — |
| RTX 3090 | 24 GB | Does not fit | — |
| RTX 4090 | 24 GB | Does not fit | — |
| RTX 5090 | 32 GB | Does not fit | — |
| RX 7900 XTX | 24 GB | Does not fit | — |
| 2 × RTX 3090 | 48 GB | Does not fit | — |
| 4 × RTX 3090 | 96 GB | Does not fit | — |
| Mac M4 Max 128 GB | 96 GB | Does not fit | — |
| Ryzen AI Max+ 395 128 GB | 96 GB | Does not fit | — |
| 8 × H100 SXM | 640 GB | Fits in GPU | 14 tok/s |
Estimate at 4-bit with 32K context, 64 GB of DDR5 for offload. Speed ≈ memory bandwidth × 70% ÷ data read per token; real numbers vary by about ±30%.
GPU memory needed
| Level | 8K context | 32K context | 128K context | Quality vs full |
|---|---|---|---|---|
| Q3_K_M | 383 GB | 385 GB | 393 GB | +4.7% noticeable loss |
| Q4_K_M | 464 GB | 466 GB | 474 GB | +1.2% very small loss |
| Q5_K_M | 544 GB | 546 GB | 554 GB | +0.4% near-lossless |
| Q6_K | 627 GB | 629 GB | 637 GB | +0.2% near-lossless |
| Q8_0 | 812 GB | 814 GB | 822 GB | ≈ 0% same as full |
| F16 | 1528 GB | 1530 GB | 1538 GB | ≈ 0% same as full |
Weights + context cache (from the model's architecture) + runtime. Quality: increase in perplexity against the full model, from llama.cpp tests, scaled by model size. Simulate your own setup.