Can I run it?
Can I run gemma 4 31B it on RTX 6000 Ada?
Runs
Runs fully on your RTX 6000 Ada at UD-Q8_K_XL, 8K context, about 12–17 tok/s. Weights 32.6 GB plus 2.03 GB of KV cache — 35.3 GB of 45.1 GB usable. Up to 64K context still fits.
Best quantUD-Q8_K_XL
Working context8K
Max that fits64K
Speed12–17 tok/sEstimate from memory bandwidth, not a benchmark. Method.
Weights32.6 GB
KV cache2.03 GB
Total35.3 GB
Usable45.1 GB
gemma 4 31B it details · RTX 6000 Ada page · How this estimate is made
Run commands
llama.cpp
llama-server -hf unsloth/gemma-4-31B-it-GGUF:UD-Q8_K_XL -c 8192 -ngl 60
Ollama
ollama run gemma
LM Studio
lms get unsloth/gemma-4-31B-it-GGUF # Then load quant UD-Q8_K_XL
Assumptions
- Estimate from memory bandwidth, not a benchmark. Decode speed uses 55–75% of peak bandwidth.
- KV cache is FP16. Engine overhead assumes llama.cpp (0.3 GB + 1% of the weights). Ollama is closer to 0.9 GB + 3%, LM Studio closer to 1 GB + 3%.
- UD-Q8_K_XL size is the real GGUF file size from Hugging Face.
- 0.5 GB is reserved because this GPU also drives a display, then 5% of the rest is left free.
- Speed is quoted at 8K context, not at the maximum context that still fits.
Larger models that also fit
- Can I run Qwen3.6 35B A3B on RTX 6000 Ada? — Runs, UD-Q8_K_XL, 33–46 tok/s (estimate)
- Can I run Qwen3.8 35B A3B Distill on RTX 6000 Ada? — Runs, Q8_0, 34–46 tok/s (estimate)
- Can I run Qwen3.5 35B A3B on RTX 6000 Ada? — Runs, Q8_0, 35–47 tok/s (estimate)
Updated 2026-10-24. Profile on this page is the device default plus 32 GB of DDR5-5600 system RAM.