Qwen · 125B · MoE
Can you run Qwen3.8-Flash-Next locally?
Qwen3.8-Flash-Next is a mixture-of-experts model with 125B parameters, 6B active per token. At 4-bit or better it runs on 10 of the 120 hardware configurations listed here; the smallest is the DGX Spark (GB10) (128 GB). On a 128 GB DGX Spark it runs at Q4_K_XL, at roughly 28 tokens per second (our est.).
Data as of 2 November 2026
Fastest machines for Qwen3.8-Flash-Next
Every machine that runs it, fastest first. Filter by type; your machine is marked. Compare machines running it side by side
- 1RTX PRO 6000 BlackwellGraphics card · 96 GB~228 tok/s our est.Q3_K_XL · 93 of 95 GB 3-bit only
- 22x RTX PRO 6000 BlackwellGraphics card · 192 GB~167 tok/s ModelFit est.Q4_K_XL · 115 of 190 GB
- 3M5 UltraMac · 256–512 GB · 3 variants~111 tok/s ModelFit est.Q4_K_XL · 115 GB
- 4M2 UltraMac · 128 GB · 2 variants~102 tok/s our est.Q3_K_XL · 93 GB 3-bit only
- 5M1 UltraMac · 128 GB · 2 variants~102 tok/s our est.Q3_K_XL · 93 GB 3-bit only
- 6M3 UltraMac · 256–512 GB · 3 variants~76 tok/s ModelFit est.Q4_K_XL · 115 GB
- 7M4 Max · 128 GB · 40cMac · 128 GB~70 tok/s our est.Q3_K_XL · 93 of 96 GB 3-bit only
- 8M2 UltraMac · 192 GB · 2 variants~68 tok/s ModelFit est.Q4_K_XL · 115 GB
- 9M3 Max · 128 GB · 40cMac · 128 GB~51 tok/s our est.Q3_K_XL · 93 of 96 GB 3-bit only
- 10Ryzen AI Max+ 395 · 128 GBAI mini PC · 128 GB~33 tok/s our est.Q3_K_XL · 93 of 96 GB 3-bit only
- 11DGX Spark (GB10)AI mini PC · 128 GB~28 tok/s our est.Q4_K_XL · 115 of 122 GB
- 12M5 Max · 128 GB · 40cMac · 128 GBno estimateQ3_K_XL · 93 of 96 GB 3-bit only
Too big for 101 machines
M5 Ultra · 96 GB · 80c, M5 Ultra · 96 GB · 64c, M3 Ultra · 96 GB · 80c, M3 Ultra · 96 GB · 60c, M2 Ultra · 96 GB, M3 Max · 96 GB · 30c, M2 Max · 96 GB · 38c, 2x RTX 5090, Ryzen AI Max+ 395 · 64 GB, M2 Ultra · 64 GB · 76c, M2 Ultra · 64 GB · 60c, M1 Ultra · 64 GB · 64c, M1 Ultra · 64 GB · 48c, M5 Max · 64 GB · 40c, M4 Max · 64 GB · 40c, M3 Max · 64 GB · 40c, M2 Max · 64 GB · 38c, M2 Max · 64 GB · 30c, M1 Max · 64 GB · 32c, M1 Max · 64 GB · 24c, M5 Pro · 64 GB · 20c, M5 Pro · 64 GB · 16c, M4 Pro · 64 GB · 20c, M4 Pro · 64 GB · 16c, 2x RTX 4090, 2x RTX 3090 Ti, 2x RTX 3090, 2x RX 7900 XTX, M5 Max · 48 GB · 40c, M4 Max · 48 GB · 40c, M3 Max · 48 GB · 40c, M5 Pro · 48 GB · 20c, M5 Pro · 48 GB · 16c, M4 Pro · 48 GB · 20c, M4 Pro · 48 GB · 16c, RTX 5090, M5 Max · 36 GB · 32c, M4 Max · 36 GB · 32c, M3 Max · 36 GB · 30c, M3 Pro · 36 GB, RTX 4090, RTX 3090 Ti, RTX 3090, RX 7900 XTX, M2 Max · 32 GB · 38c, M2 Max · 32 GB · 30c, M1 Max · 32 GB · 32c, M1 Max · 32 GB · 24c, M2 Pro · 32 GB, M1 Pro · 32 GB, M6 · 32 GB · 12c, M5 · 32 GB · 10c, M5 · 32 GB · 8c, M4 · 32 GB, RX 7900 XT, M5 Pro · 24 GB · 20c, M5 Pro · 24 GB · 16c, M4 Pro · 24 GB · 20c, M4 Pro · 24 GB · 16c, M6 · 24 GB · 12c, M6 · 24 GB · 10c, M5 · 24 GB · 10c, M5 · 24 GB · 8c, M4 · 24 GB, M3 · 24 GB, M2 · 24 GB, RTX 5080, RTX 5070 Ti, RTX 5060 Ti, RTX 4080 SUPER, RTX 4080, RTX 4070 Ti SUPER, RTX 4060 Ti, Tesla T4, Tesla P100, RX 9070 XT, RX 9060 XT, M3 Pro · 18 GB, RTX 5070, RTX 4070 Ti, RTX 4070 SUPER, RTX 4070, RTX 3060, M2 Pro · 16 GB, M1 Pro · 16 GB, M6 · 16 GB · 12c, M6 · 16 GB · 10c, M5 · 16 GB · 10c, M5 · 16 GB · 8c, M4 · 16 GB, M3 · 16 GB, M2 · 16 GB, M1 · 16 GB, RTX 5060, RTX 4060, RTX 3070, RTX 3060 Ti, RTX 2070, M3 · 8 GB, M2 · 8 GB, M1 · 8 GB. Qwen3.8-Flash-Next needs about 93 GB at its smallest build.
Speeds are single-user decode estimates, not measurements. "ModelFit est." comes from ModelFit's model fitted on published runs (CC BY 4.0); "our est." is memory bandwidth divided by bytes read per token, times 0.55. Memory is what the best build needs, against what the machine can give a model. Method
DGX Spark setup notes: GPUwerk guide for Qwen3.8-Flash-Next.
About the model
- Parameters
- 125B
- Active per token
- 6B
- Type
- Mixture of experts
- Good for
- Large fast MoE for chat and agents
- Model card
- Hugging Face
- Hugging Face count
- 180B (Hugging Face total includes a 51B n-gram table and a 4B MTP head on top of the 125B model.)
Builds and how to run them
| Quantization | Load | Min. RAM | Command |
|---|---|---|---|
| Q4_K_XL | 111 GB | 192 GB | GGUF or MLX build |
| IQ4_XS | 94 GB | 128 GB | GGUF or MLX build |
| Q3_K_XL | 90 GB | 128 GB | GGUF or MLX build |
Load, minimum RAM and Ollama commands: ModelFit, CC BY 4.0. Load is memory with the model loaded, before long contexts.
Questions
Can I run Qwen3.8-Flash-Next on a Mac?
Yes on a Mac with enough memory: the smallest Apple configuration listed here that runs it at 4-bit or better is the M2 Ultra · 192 GB · 76c.
How much memory does Qwen3.8-Flash-Next need?
About 93 GB at the smallest build in our data, including a margin for the runtime and an 8K-token context. Longer contexts need more.
Does Qwen3.8-Flash-Next run on a DGX Spark?
Yes, at Q4_K_XL. The Spark has 128 GB of unified memory, about 121.6 GB usable.