RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Llama 3.1 70B run on the H200?

Yes. At 8K context the best fit is Q8_0, using about 73.0 GB of the 134 GB usable on the H200. Estimated speed ceiling: ~64 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •26.5 GB Fits27.7 GB Fits35.2 GB Fits65.2 GB Fits182
3-bit (Q3_K_M) •33.8 GB Fits35.1 GB Fits42.6 GB Fits72.6 GB Fits140
4-bit (Q4_K_M) •41.5 GB Fits42.7 GB Fits50.2 GB Fits80.2 GB Fits113
5-bit (Q5_K_M) •48.4 GB Fits49.7 GB Fits57.2 GB Fits87.2 GB Fits96
6-bit (Q6_K) •55.8 GB Fits57.1 GB Fits64.6 GB Fits94.6 GB Fits83
8-bit (Q8_0) •71.7 GB Fits73.0 GB Fits80.5 GB Fits110 GB Fits64
16-bit (F16/BF16) •133 GB Tight135 GB No142 GB No172 GB No—

• real GGUF file size from ThomasBaruzier/Llama-3.3-70B-Instruct-GGUF. Speed is a bandwidth ceiling (4800 GB/s), not a benchmark. Methodology.

More

Llama 3.1 70B on every GPU and Mac · Every model that runs on the H200 · Other models that fit 64 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (meta-llama/Llama-3.1-70B), NVIDIA specs. Data as of 2026-11-17.