Can Qwen3.8 Flash Next run on the H100 PCIe?
Yes. At 8K context the best fit is Q2_K, using about 63.9 GB of the 76.0 GB usable on the H100 PCIe. Estimated speed ceiling: ~87 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) | 63.8 GB Fits | 63.9 GB Fits | 64.5 GB Fits | 66.7 GB Fits | 87 |
| 3-bit (Q3_K_M) | 82.9 GB No | 83.0 GB No | 83.6 GB No | 85.8 GB No | — |
| 4-bit (Q4_K_M) | 103 GB No | 104 GB No | 104 GB No | 106 GB No | — |
| 5-bit (Q5_K_M) | 120 GB No | 121 GB No | 121 GB No | 123 GB No | — |
| 6-bit (Q6_K) | 138 GB No | 139 GB No | 139 GB No | 141 GB No | — |
| 8-bit (Q8_0) • | 176 GB No | 176 GB No | 177 GB No | 179 GB No | — |
| 16-bit (F16/BF16) • | 331 GB No | 331 GB No | 331 GB No | 334 GB No | — |
• real GGUF file size from unsloth/Qwen3.8-Flash-Next-GGUF. Speed is a bandwidth ceiling (2000 GB/s), not a benchmark. Methodology.
More
Qwen3.8 Flash Next on every GPU and Mac · Every model that runs on the H100 PCIe · Other models that fit 64 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (Qwen/Qwen3.8-Flash-Next), NVIDIA specs. Data as of 2026-11-17.