All models › minimax
Arena score1399#94 of 144 in Coding, paid models included
Size228.7 B11 B active per token (mixture of experts)
4-bit download139 GBweights only, Q4_K_M
Max context200Ktokens, from the model config
Where to use it for free
- The lab's own chat: agent.minimax.io (free with daily limits)
- Download and run it at home: official weights · GGUF files for Ollama and LM Studio
Arena scores
| Arena | Score | Rank | Votes |
|---|---|---|---|
| Coding | 1399 | #94 of 144 | 16K |
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 | 129 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 | 117 GB | 123 GB | 148 GB | +4.7% noticeable loss |
| Q4_K_M | 141 GB | 148 GB | 172 GB | +1.2% very small loss |
| Q5_K_M | 165 GB | 172 GB | 196 GB | +0.4% near-lossless |
| Q6_K | 190 GB | 196 GB | 221 GB | +0.2% near-lossless |
| Q8_0 | 246 GB | 252 GB | 277 GB | ≈ 0% same as full |
| F16 | 460 GB | 466 GB | 491 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
- Qwen3.5-397B-A17B 1400 · 403.4 B
- Inkling Small 1409
- MiniMax-M2.5 1386 · 228.7 B
- Inkling 1414
- MiniMax-M2.1 Preview 1384 · 228.7 B
- Gemma 4 31B 1367 · 31.3 B