Yes — with 37.4 GB to spare
Qwen3.8-Flash-Next 180B-A6B at Q4_K_M fits your H200 SXM entirely on the GPU at 8K context, at an estimated 331 tokens per second. There is room for its full 256K window.
The open preview of the Qwen4 architecture: a 125B-A6B hybrid (Gated DeltaNet + sparse attention, KV cache on 12 of 48 blocks) plus a 51B n-gram embedding and a 4B draft head — 180B on disk, 6B active. The hosted "Qwen3.8-Flash" is this model with a 1M window.
The VRAM budget
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| Q8_0 | 178.1 GB | 178.9 GB | — | ~10 | −0.1% ppl | 39.5 GB over |
| Q6_K | 137.5 GB | 138.3 GB | 57K | 244 | −0.4% ppl | Long context |
| Q5_K_M | 118.8 GB | 119.6 GB | 256K | 282 | −0.8% ppl | Long context |
| Q4_K_M | 101.2 GB | 102.0 GB | 256K | 331 | −1.9% ppl | Recommended |
| Q3_K_M | 81.9 GB | 82.7 GB | 256K | 409 | −5.4% ppl | Long context |
| Q2_K | 70.2 GB | 71.0 GB | 256K | 478 | −15% ppl | Long context |
Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it. Only 12 of its 48 blocks keep a per-token KV cache; the rest are linear-attention, Mamba or convolution blocks with a fixed-size state.
How to run it
$ ollama pull qwen3.8-flash-next:125b-a6b-nvfp4 $ OLLAMA_CONTEXT_LENGTH=8192 \ ollama run qwen3.8-flash-next:125b-a6b-nvfp4
The default. One binary, a model registry, an OpenAI-compatible port. More on Ollama.