Can I run this LLM?
Can a NVIDIA RTX Pro 6000 Blackwell (96GB) run Qwen3.8 Flash Next (MoE)?
Qwen · See model card · estimated for a 96.0 GB machine at 4K context.
Yes, but it's tight.
Tight / slowBest fit: Qwen3.8 Flash Next (MoE) at Q2_K · 80.9 GB weights · 205–307 tok/s on a NVIDIA RTX Pro 6000 Blackwell (96GB).
Arena Text Overall · style-controlled
UnratedAmbiguous matchAmbiguous Arena identity; unrated
Arena identity is ambiguous. No exact configuration is present in the latest Overall entry set. No related-family rating is inherited. No rating is assigned or used for ranking. Local quantization quality is unmeasured.
Snapshot published 2026-10-08 · snapshot imported 2026-10-11 UTC · validated last-good data · manual refresh
Arena leaderboard dataset · Arena / lmarena-ai, Arena Leaderboard Dataset (CC BY 4.0). Selected Text Overall style-controlled rows; field names adapted, ratings unchanged. · dataset CC BY 4.0 · revision e16f90232986
- Total memory at 4K context
- 81.8 GB
- Weights + KV cache + runtime overhead
- Estimated generation
- 205–307 tok/s
- Estimated first token
- ~0.6s
Every quantization on this machine
On small screens, each quant lists every metric below its name. On wider screens, scroll sideways for total memory, speed and fit. Keyboard: focus the table, then use the arrow keys. Quant names stay visible.
| Quant | Weights | Total memory | Speed | Fit |
|---|---|---|---|---|
| Q2_K | 80.9 GB | 81.8 GB | 205–307 tok/s | Tight / slow |
| Q3_K_M | 92.0 GB | 92.9 GB | — not resident | Won't fit |
| Q4_K_M | 119.6 GB | 120.5 GB | — not resident | Won't fit |
| Q5_K_M | 134.7 GB | 135.6 GB | — not resident | Won't fit |
| Q6_K | 168.1 GB | 169.0 GB | — not resident | Won't fit |
| Q8_0 | 188.3 GB | 189.2 GB | — not resident | Won't fit |
| FP16 | 354.0 GB | 354.9 GB | — not resident | Won't fit |
Ran Qwen3.8 Flash Next (MoE) on a NVIDIA RTX Pro 6000 Blackwell (96GB)? Add your real numbers →