Can I run it?
Can I run GLM 4.7 Flash on NVIDIA H100 SXM 80GB?
Runs
Runs fully on your NVIDIA H100 SXM 80GB at BF16, 8K context, about 74–101 tok/s. Weights 55.8 GB plus 0.41 GB of KV cache — 57.1 GB of 76.0 GB usable. Up to 198K context still fits.
Best quantBF16
Working context8K
Max that fits198K
Speed74–101 tok/sEstimate from memory bandwidth, not a benchmark. Method.
Weights55.8 GB
KV cache0.41 GB
Total57.1 GB
Usable76.0 GB
GLM 4.7 Flash details · NVIDIA H100 SXM 80GB page · How this estimate is made
Run commands
llama.cpp
llama-server -hf unsloth/GLM-4.7-Flash-GGUF:BF16 -c 8192 -ngl 47
Ollama
ollama run glm-4.7-flash
LM Studio
lms get unsloth/GLM-4.7-Flash-GGUF # Then load quant BF16
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%.
- 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 Qwen3.6 35B A3B on NVIDIA H100 SXM 80GB? — Tight fit, BF16, 65–88 tok/s (estimate)
- Can I run Qwen3.8 35B A3B Distill on NVIDIA H100 SXM 80GB? — Tight fit, BF16, 63–86 tok/s (estimate)
- Can I run Qwen3.8 Flash Next on NVIDIA H100 SXM 80GB? — Heavily degraded, UD-IQ1_M, 60–82 tok/s (estimate)
Updated 2026-10-24. Profile on this page is the device default plus 32 GB of DDR5-5600 system RAM.