FreeLLMAll models › Compare
deepseek-v4.1-flash-max vs Gemma 4 31B
deepseek-v4.1-flash-max is ahead on Arena (1463 vs 1443): in a blind vote people prefer it about 53% of the time.
deepseek-v4.1-flash-max1463Arena chat · #38 of 416
Gemma 4 31B1443Arena chat · #67 of 416
Arena scores by category
| Category | deepseek-v4.1-flash-max | Gemma 4 31B | Ahead |
|---|---|---|---|
| Chat | 1463 | 1443 | deepseek-v4.1-flash-max |
| Vision | 1277 | 1277 | about even |
Scores from blind human votes on Arena. A gap under 10 points is too small to call.
Size and where to use them free
| deepseek-v4.1-flash-max | Gemma 4 31B | |
|---|---|---|
| Made by | deepseek | |
| Size | 763.2 B (228.1 B active) | 31.3 B |
| 4-bit download | 464 GB | 20 GB |
| Use it free | download and run at home · MIT license | free API on OpenRouter · download and run at home · Apache 2.0 license |
Speed at home
| Hardware | deepseek-v4.1-flash-max | Gemma 4 31B |
|---|---|---|
| RTX 3090 | does not fit | 33 tok/s |
| RTX 4090 | does not fit | 36 tok/s |
| RTX 5090 | does not fit | 62 tok/s |
| RX 7900 XTX | does not fit | 34 tok/s |
| Mac M4 Max 128 GB | does not fit | 19 tok/s |
| Ryzen AI Max+ 395 128 GB | does not fit | 9.4 tok/s |
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.
More comparisons
- deepseek-v4.1-flash-max vs MiMo-V2.6-Pro
- deepseek-v4.1-flash-max vs Kimi K3 (Max)
- deepseek-v4.1-flash-max vs GLM-5.3 (Max)
- deepseek-v4.1-flash-max vs GLM-5.3-Flash
- deepseek-v4.1-flash-max vs GLM-5.2 (Max)
- deepseek-v4.1-flash-max vs MiMo-V2.5-Pro
- Gemma 4 31B vs MiMo-V2.6-Pro
- Gemma 4 31B vs Kimi K3 (Max)
- Gemma 4 31B vs GLM-5.3 (Max)
- Gemma 4 31B vs GLM-5.3-Flash