← CanIRunLocal · All hardware · All models
No. Qwen3.8-Flash-Next 125B-A6B (MoE) does not fit on RTX 5090 32GB: Q4_K_M needs 122.7 GB and 31.5 GB is usable.
Hardware: RTX 5090 32GB · Model: Qwen3.8-Flash-Next 125B-A6B (MoE)
RTX 5090 32GB has 32 GB of VRAM and 1792 GB/s of memory bandwidth. The checker holds back 0.5 GB of VRAM for the driver and assumes 16 GB of system RAM, so fast memory usable by Ollama is 31.5 GB. Partial offload may also use 60% of that system RAM. Qwen3.8-Flash-Next 125B-A6B (MoE) (125B, 6B active, Alibaba) at Q4_K_M is a 120 GB download and needs 122.7 GB with headroom for about 8k tokens.
| Best quant | Q4_K_M |
|---|---|
| Download size | 120 GB |
| Memory needed | 122.7 GB |
| Usable fast memory | 31.5 GB |
| Fit | does not fit |
| Estimated speed | no estimate, it does not fit |
| Command | ollama run qwen3.8-flash-next:125b-a6b-q4_K_M |
Smallest hardware that runs it: M2 Ultra 192GB at Q4_K_M (fits in fast memory, 122.7 GB needed, 144.0 GB usable, about 56 tok/s (estimate)). Can a M2 Ultra 192GB run Qwen3.8-Flash-Next 125B-A6B (MoE)?
A smaller Alibaba model that fits this hardware: Qwen3.5 35B-A3B (MoE) at Q4_K_M (fits in fast memory, 23.9 GB). Can a RTX 5090 32GB run Qwen3.5 35B-A3B (MoE)?
Open RTX 5090 32GB in the checkerEstimates, not benchmarks. Model sizes are ollama.com download sizes; memory needed adds headroom for ~8k tokens of context; speeds are rough figures from memory bandwidth. Data updated 2026-10-23.
A project by OnDevice Labs · llms.txt