Can flint run on the H200?
Yes. At 8K context the best fit is F16, using about 75.1 GB of the 134 GB usable on the H200. Estimated speed ceiling: ~1920 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) | 14.7 GB Fits | 14.8 GB Fits | 15.5 GB Fits | 18.1 GB Fits | 10239 |
| 3-bit (Q3_K_M) | 18.9 GB Fits | 19.0 GB Fits | 19.7 GB Fits | 22.3 GB Fits | 7856 |
| 4-bit (Q4_K_M) | 23.5 GB Fits | 23.6 GB Fits | 24.2 GB Fits | 26.9 GB Fits | 6282 |
| 5-bit (Q5_K_M) | 27.2 GB Fits | 27.3 GB Fits | 28.0 GB Fits | 30.6 GB Fits | 5389 |
| 6-bit (Q6_K) | 31.2 GB Fits | 31.3 GB Fits | 32.0 GB Fits | 34.6 GB Fits | 4682 |
| 8-bit (Q8_0) • | 40.2 GB Fits | 40.3 GB Fits | 41.0 GB Fits | 43.6 GB Fits | 3611 |
| 16-bit (F16/BF16) • | 74.9 GB Fits | 75.1 GB Fits | 75.7 GB Fits | 78.3 GB Fits | 1920 |
• real GGUF file size from unsloth/flint-GGUF. Speed is a bandwidth ceiling (4800 GB/s), not a benchmark. Methodology.
More
flint 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 (RecursiveSI/flint), NVIDIA specs. Data as of 2026-11-17.