Smaller alternatives
Models that need less memory than Qwen3.5 122B A10B and score about as well or better.
Qwen3.5 122B A10B
MoEVision
Qwen · 125.1B (10B active) · Mixture of experts
Qwen3.5 122B A10B is a 125.1B model from Qwen with a 256K-token context. At Q4_K_M with an 8K context it needs about 71.8 GB; 91 GB leaves room for longer chats.
Mixture of experts
Parameters: 125.1B · Active: 10B
All 125.1B parameters load into memory, but only 10B 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 | 71.7 GB |
| 8K | 0.2 GB | 71.8 GB |
| 32K | 0.8 GB | 72.3 GB |
| 128K | 3 GB | 74.6 GB |
| 256K | 6 GB | 77.6 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 122B A10B grade A or S at Q4_K_M.
Can I run Qwen3.5 122B A10B locally?
Can I run Qwen3.5 122B A10B locally?
Yes, if your GPU or Mac has about 71.8 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 122B A10B need?
About 71.8 GB at Q4_K_M with an 8K context and 121.4 GB at Q8_0. Lower quantizations fit smaller cards with some loss in quality; longer contexts add to the total.