FreeLLMAll models › Compare
Gemma 4 31B vs MiMo-V2.6-Flash
MiMo-V2.6-Flash is ahead on Arena (1455 vs 1443): in a blind vote people prefer it about 52% of the time.
Gemma 4 31B1443Arena chat · #67 of 416
MiMo-V2.6-Flash1455Arena chat · #45 of 416
Arena scores by category
| Category | Gemma 4 31B | MiMo-V2.6-Flash | Ahead |
|---|---|---|---|
| Chat | 1443 | 1455 | MiMo-V2.6-Flash |
| Coding | 1368 | 1633 | MiMo-V2.6-Flash |
| Vision | 1277 | 1259 | Gemma 4 31B |
Scores from blind human votes on Arena. A gap under 10 points is too small to call.
Size and where to use them free
| Gemma 4 31B | MiMo-V2.6-Flash | |
|---|---|---|
| Made by | xiaomi | |
| Size | 31.3 B | 310.8 B (17.4 B active) |
| 4-bit download | 20 GB | 190 GB |
| Use it free | free API on OpenRouter · download and run at home · Apache 2.0 license | download and run at home · MIT license |
Speed at home
| Hardware | Gemma 4 31B | MiMo-V2.6-Flash |
|---|---|---|
| RTX 3090 | 33 tok/s | does not fit |
| RTX 4090 | 36 tok/s | does not fit |
| RTX 5090 | 62 tok/s | does not fit |
| RX 7900 XTX | 34 tok/s | does not fit |
| Mac M4 Max 128 GB | 19 tok/s | does not fit |
| Ryzen AI Max+ 395 128 GB | 9.4 tok/s | does not fit |
Estimates at 4-bit with an 8K context, 64 GB of system RAM for offload, calibrated on 44 real llama.cpp tests.
Try them yourself
Ask both the same question side by side in Try & compare, or vote blind between free models in Free Arena.