Qwen3.8 Flash Next VRAM requirements
Qwen · 180B params (6B active) · Qwen Community License. Estimates, not vendor numbers.
Qwen3.8 Flash Next (180B parameters, 6B active per token) needs about 110 GB of VRAM or unified memory at Q4, 130 GB at Q5 and 193 GB at Q8 (weights plus about 1.5 GB headroom, our estimate). It is too large for the consumer setups we list; it needs a multi-GPU rig or a very large-memory Mac or server.
| Quant | Download | Memory needed |
|---|---|---|
| Q4 | 108 GB | 110 GB |
| Q5 | 128 GB | 130 GB |
| Q8 | 191 GB | 193 GB |
Will it run on my machine?
| Setup | Runs? | Speed est. |
|---|---|---|
| 8GB GPU (RTX 4060) | No | n/a |
| 12GB GPU (RTX 3060 / 4070) | No | n/a |
| 16GB GPU (RTX 4060 Ti 16GB) | No | n/a |
| 24GB GPU (RTX 4090) | No | n/a |
| 32GB GPU (RTX 5090) | No | n/a |
| Mac 16GB (M4) | No | n/a |
| Mac 48GB (M4 Pro) | No | n/a |
| Mac 128GB (M4 Max) | No | n/a |
| PC, 32GB RAM, no GPU | No | n/a |
Best quant that fits each setup, with estimated generation speed from memory bandwidth. Real speed depends on the runtime, context length and settings.
Experimental preview. Mixture of experts: 125B with 6B active, plus 51B n-gram embedding and 4B MTP (Qwen). We count all 180B for memory.
FAQ
How much VRAM does Qwen3.8 Flash Next need?
About 110 GB at Q4, 130 GB at Q5 and 193 GB at Q8, including about 1.5 GB headroom. These are estimates from the parameter count on the official model card.
Can Qwen3.8 Flash Next run on 8GB of VRAM?
Not fully on the GPU. At Q4 it needs about 110 GB; partial CPU offload works but is much slower.
Can Qwen3.8 Flash Next run on a Mac?
Not on the Mac configurations we list; it needs more unified memory.
Which quant of Qwen3.8 Flash Next should I use?
Use the highest quant that fits with room to spare: Q8 is near full quality, Q5 is a good balance, and Q4 is the smallest that usually keeps quality acceptable.
Why is Qwen3.8 Flash Next fast for its size?
It is a mixture of experts: 180B parameters in total but only 6B are used per token, so it reads less memory per token. You still need memory for all 180B.
Similar-size models
Gemma 4 31B (30.7B) · DeepSeek R1 Distill Qwen 32B (32.8B) · Qwen3.6 35B A3B (35B) · Llama 3.3 70B Instruct (70B) · gpt-oss-120b (117B) · Mistral Small 4 (119B)