Gemma4 31B
23 records across 5 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| RTX Pro 6000 Blackwell | Gemma4 31B 31B | Q4_K | llama.cpp | 61.6 | 3749.8 | – | – | 4096 | – | sourced | – | source |
| RTX 5090 | Gemma4 31B 31B | Q4_K | llama.cpp | 61.1 | 3395.0 | – | – | 4096 | – | sourced | – | source |
| RTX Pro 6000 Blackwell | Gemma4 31B 31B | Q4_K | llama.cpp | 59.6 | 3061.9 | – | – | 16384 | – | sourced | – | source |
| RTX 5090 | Gemma4 31B 31B | Q4_K | llama.cpp | 59.2 | 2794.3 | – | – | 16384 | – | sourced | – | source |
| RTX Pro 6000 Blackwell | Gemma4 31B 31B | Q4_K | llama.cpp | 55.8 | 2086.7 | – | – | 32768 | – | sourced | – | source |
| RTX 5090 | Gemma4 31B 31B | Q4_K | llama.cpp | 55.4 | 2229.1 | – | – | 32768 | – | sourced | – | source |
| RTX Pro 6000 Blackwell | Gemma4 31B 31B | Q4_K | llama.cpp | 52.0 | 1423.0 | – | – | 65536 | – | sourced | – | source |
| RTX 5090 | Gemma4 31B 31B | Q4_K | llama.cpp | 51.6 | 1459.3 | – | – | 65536 | – | sourced | – | source |
| RTX Pro 6000 Blackwell | Gemma4 31B 31B | Q4_K | llama.cpp | 43.6 | 876.8 | – | – | 131072 | – | sourced | – | source |
| RTX 5090 | Gemma4 31B 31B | Q4_K | llama.cpp | 43.4 | 900.2 | – | – | 131072 | – | sourced | – | source |
| RTX 3090 | Gemma4 31B 31B | Q4_K | llama.cpp | 34.7 | 1155.8 | – | – | 4096 | – | sourced | – | source |
| RTX Pro 6000 Blackwell | Gemma4 31B 31B | Q4_K | llama.cpp | 34.4 | 506.8 | – | – | 262144 | – | sourced | – | source |
| RTX 3090 | Gemma4 31B 31B | Q4_K | llama.cpp | 33.5 | 913.2 | – | – | 16384 | – | sourced | – | source |
| Radeon RX 7900 XTX | Gemma4 31B | Q8_0 | llama.cpp (ROCm) | 32.35 | 1114.17 | – | – | tg128 | 2026-08-23 | community | – | source |
| RTX 3090 | Gemma4 31B 31B | Q4_K | llama.cpp | 31.4 | 723.7 | – | – | 32768 | – | sourced | – | source |
| Radeon RX 7900 XTX | Gemma4 31B | Q8_0 | llama.cpp (Vulkan) | 24.42 | 851.56 | – | – | tg128 | 2026-08-23 | community | – | source |
| Radeon RX 7900 XTX | Gemma4 31B | Q8_0 | llama.cpp (ROCm) | 23.43 | 960.35 | – | – | tg128 | 2026-08-23 | community | – | source |
| Radeon RX 7900 XTX | Gemma4 31B | Q8_0 | llama.cpp (ROCm) | 22.97 | 920.55 | – | – | tg128 | 2026-08-23 | community | – | source |
| Radeon RX 7900 XTX | Gemma4 31B | Q8_0 | llama.cpp (Vulkan) | 21.03 | 609.25 | – | – | tg128 | 2026-08-23 | community | – | source |
| Arc Pro B60 | Gemma4 31B | Q4_0 | llama.cpp | 19.64 | 146.16 | – | – | tg128 | 2026-08-29 | community | – | source |
| Arc Pro B60 | Gemma4 31B | Q4_0 | llama.cpp | 19.63 | 210.16 | – | – | tg128 | 2026-08-29 | community | – | source |
| Arc Pro B60 | Gemma4 31B | Q4_0 | llama.cpp | 18.94 | 472.95 | – | – | tg128 | 2026-08-29 | community | – | source |
| Arc Pro B60 | Gemma4 31B | Q4_0 | llama.cpp | 18.92 | 127.18 | – | – | tg128 | 2026-08-29 | community | – | source |