Smaller alternatives
Models that need less memory than Qwen3.5 397B A17B and score about as well or better.
Qwen3.5 397B A17B
MoEVision
Qwen · 403.4B (17B active) · Mixture of experts
Qwen3.5 397B A17B is a 403.4B model from Qwen with a 256K-token context. At Q4_K_M with an 8K context it needs about 227.9 GB; 286 GB leaves room for longer chats.
Mixture of experts
Parameters: 403.4B · Active: 17B
All 403.4B parameters load into memory, but only 17B work on each token, so it runs at the speed of a much smaller model.
Quantization options
| Quant | Bits | Memory | Quality | On your hardware |
|---|---|---|---|---|
| Q2_K | 3.16 | — | Noticeably worse | … |
| Q3_K_M | 4 | — | Some loss | … |
| Q4_K_M | 4.89 | — | Good | … |
| Q5_K_M | 5.7 | — | Good | … |
| Q6_K | 6.56 | — | Near original | … |
| Q8_0 | 8.5 | — | Near original | … |
| F16 | 16 | — | Original | … |
Memory by context length
At Q4_K_M. The context cache grows with every token the model keeps in mind.
| Context | Context cache | Total |
|---|---|---|
| 4K | 0.1 GB | 227.7 GB |
| 8K | 0.2 GB | 227.9 GB |
| 32K | 0.9 GB | 228.6 GB |
| 128K | 3.8 GB | 231.4 GB |
| 256K | 7.5 GB | 235.1 GB |
Next steps
Compare it with
Scored models of a similar size, side by side on your device.
Least hardware that runs it well
Desktop devices with the least memory that give Qwen3.5 397B A17B grade A or S at Q4_K_M.
Can I run Qwen3.5 397B A17B locally?
Can I run Qwen3.5 397B A17B locally?
Yes, if your GPU or Mac has about 227.9 GB free for it at Q4_K_M. Open this page on that computer to see the grade for your exact hardware, then start it with llama.cpp, Ollama or LM Studio.
How much memory does Qwen3.5 397B A17B need?
About 227.9 GB at Q4_K_M with an 8K context and 393.1 GB at Q8_0. Lower quantizations fit smaller cards with some loss in quality; longer contexts add to the total.