All models › deepseek
Arena score1463#38 of 416 in Chat, paid models included
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
- The lab's own chat: chat.deepseek.com (free with daily limits)
- Download and run it at home: official weights · GGUF files for Ollama and LM Studio
Arena scores
Rank among all models, paid ones included. Source: Arena leaderboard dataset.
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.
Chat score over time
14501475150015251550
MayJunJulAugSeptOct
deepseek-v4.1-flash-max 1463Best paid model
Arena score from 17 Apr 2026 to 15 Oct 2026.
Similar free models in Chat
- GLM-5.1 1462 · 753.9 B
- MiMo-V2.5-Pro 1465 · 1023.2 B
- GLM-5.2 (Max) 1470 · 753.3 B
- GLM-5.3 (Max) 1471 · 753.3 B
- GLM-5.3-Flash 1471 · 321.3 B
- Kimi K2.6 1455 · 1026.9 B