Can I run it?

Can I run Qwen3.8 4B Distill on NVIDIA H100 SXM 80GB?

Runs great

Runs great fully on your NVIDIA H100 SXM 80GB at BF16, 8K context, about 206–281 tok/s. Weights 8.07 GB plus 0.27 GB of KV cache — 8.72 GB of 76.0 GB usable. Up to 256K context still fits.

Qwen3.8 4B Distill details · NVIDIA H100 SXM 80GB page · How this estimate is made

Run commands

llama-server -hf empero-ai/Qwen3.8-4B-Distill-GGUF:BF16 -c 8192 -ngl 32

ollama run qwen3.8

lms get empero-ai/Qwen3.8-4B-Distill-GGUF
# Then load quant BF16

Assumptions

• Estimate, not a benchmark. Decode speed uses a memory-bandwidth model at 55–75% of peak.
• 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%.
• BF16 size is the real GGUF file size from Hugging Face.
• CPU runs keep about 4 GB plus a 10% cushion for the OS.
• Speed is quoted at 8K context, not at the maximum context that still fits.

Larger models that also fit

• Can I run Qwen3.8 27B on NVIDIA H100 SXM 80GB? — Runs, BF16, 33–46 tok/s
• Can I run gemma 4 12b it on NVIDIA H100 SXM 80GB? — Runs great, BF16, 68–93 tok/s
• Can I run Qwen3.5 9B on NVIDIA H100 SXM 80GB? — Runs great, BF16, 101–138 tok/s

Updated 2026-10-24. Profile on this page is the device default plus 32 GB of DDR5-5600 system RAM.