RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Qwen2.5 Coder 14B Instruct run on the H200?

Yes. At 8K context the best fit is F16, using about 29.7 GB of the 134 GB usable on the H200. Estimated speed ceiling: ~162 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctxMax tok/s (est., 8K)
2-bit (Q2_K)6.6 GB Fits7.3 GB Fits11.8 GB Fits867
3-bit (Q3_K_M)8.2 GB Fits8.9 GB Fits13.4 GB Fits665
4-bit (Q4_K_M)9.8 GB Fits10.6 GB Fits15.1 GB Fits532
5-bit (Q5_K_M)11.2 GB Fits12.0 GB Fits16.5 GB Fits456
6-bit (Q6_K)12.7 GB Fits13.5 GB Fits18.0 GB Fits396
8-bit (Q8_0)16.1 GB Fits16.8 GB Fits21.3 GB Fits306
16-bit (F16/BF16)29.0 GB Fits29.7 GB Fits34.2 GB Fits162

• real GGUF file size. Speed is a bandwidth ceiling (4800 GB/s), not a benchmark. Methodology.

More

Qwen2.5 Coder 14B Instruct 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 (Qwen/Qwen2.5-Coder-14B-Instruct), NVIDIA specs. Data as of 2026-11-17.