Can I run it?
Can I run Qwen3.8 35B A3B Distill on GeForce RTX 5080?
Tight fit
Tight fit fully on your GeForce RTX 5080 at Q2_K, 8K context, about 91–124 tok/s. Weights 12.9 GB plus 0.19 GB of KV cache — 13.5 GB of 14.7 GB usable. Up to 32K context still fits.
Best quantQ2_K
Working context8K
Max that fits32K
Speed91–124 tok/sEstimate from memory bandwidth, not a benchmark. Method.
Weights12.9 GB
KV cache0.19 GB
Total13.5 GB
Usable14.7 GB
Qwen3.8 35B A3B Distill details · GeForce RTX 5080 page · How this estimate is made
Run commands
llama.cpp
llama-server -hf empero-ai/Qwen3.8-35B-A3B-Distill-GGUF:Q2_K -c 8192 -ngl 40
Ollama
ollama run qwen3.8
LM Studio
lms get empero-ai/Qwen3.8-35B-A3B-Distill-GGUF # Then load quant Q2_K
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%.
- Q2_K 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 Cyber Tiel Coder 35B A3B GGUF MTP on GeForce RTX 5080? — Tight fit, Q2_K, 86–117 tok/s (estimate)
Updated 2026-10-24. Profile on this page is the device default plus 32 GB of DDR5-5600 system RAM.