All models › xiaomi
MiMo-V2-Flash (Non-Thinking)
xiaomi · MIT license · on Arena since 16 Oct 2026
Download
Arena score1330#119 of 144 in Coding, paid models included
Size309.8 B16.5 B active per token (mixture of experts)
4-bit download188 GBweights only, Q4_K_M
Max context256Ktokens, 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
Arena scores
| Arena | Score | Rank | Votes |
|---|---|---|---|
| Coding | 1330 | #119 of 144 | 6K |
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 | 177 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 | 156 GB | 156 GB | 159 GB | +4.7% noticeable loss |
| Q4_K_M | 189 GB | 189 GB | 192 GB | +1.2% very small loss |
| Q5_K_M | 221 GB | 222 GB | 225 GB | +0.4% near-lossless |
| Q6_K | 255 GB | 256 GB | 258 GB | +0.2% near-lossless |
| Q8_0 | 330 GB | 331 GB | 333 GB | ≈ 0% same as full |
| F16 | 620 GB | 621 GB | 624 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.
Similar free models in Coding
- DeepSeek-V3.2 1326
- Kimi K2 Thinking Turbo 1322
- GLM-4.6 1341 · 356.8 B
- Laguna M.1 1350
- Muse Glimmer 1355
- Qwen3.5-27B 1358 · 27.8 B