Qwen · 35B · MoE
Can you run Qwen3.5 35B-A3B Instruct locally?
Qwen3.5 35B-A3B Instruct is a mixture-of-experts model with 35B parameters, 3B active per token. At 4-bit or better it runs on 63 of the 120 hardware configurations listed here; the smallest is the RTX 4090 (24 GB). On a 128 GB DGX Spark it runs at Q8_0, at roughly 45 tokens per second (our est.).
Data as of 2 November 2026
Fastest machines for Qwen3.5 35B-A3B Instruct
Every machine that runs it, fastest first. Filter by type; your machine is marked. Compare machines running it side by side
- 1RTX 5090Graphics card · 32 GB~350 tok/s ModelFit est.Q4_K_M · 21 of 31 GB
- 2RTX PRO 6000 BlackwellGraphics card · 96 GB~251 tok/s ModelFit est.Q8_0 · 41 of 95 GB
- 3RTX 4090Graphics card · 24 GB~242 tok/s ModelFit est.Q4_K_M · 21 of 23 GB
- 42x RTX 5090Graphics card · 64 GB~234 tok/s ModelFit est.Q8_0 · 41 of 62 GB
- 52x RTX PRO 6000 BlackwellGraphics card · 192 GB~234 tok/s ModelFit est.Q8_0 · 41 of 190 GB
- 6RTX 3090 TiGraphics card · 24 GB~223 tok/s ModelFit est.Q4_K_M · 21 of 23 GB
- 7RTX 3090Graphics card · 24 GB~212 tok/s ModelFit est.Q4_K_M · 21 of 23 GB
- 8RX 7900 XTXGraphics card · 24 GB~168 tok/s ModelFit est.Q4_K_M · 21 of 23 GB
- 9M5 Max · 48 GB · 40cMac · 48 GB~166 tok/s ModelFit est.Q4_K_M · 21 of 36 GB
- 10M5 UltraMac · 96–512 GB · 5 variants~160 tok/s ModelFit est.Q8_0 · 41 GB
- 112x RTX 4090Graphics card · 48 GB~154 tok/s ModelFit est.Q8_0 · 41 of 46 GB
- 122x RTX 3090 TiGraphics card · 48 GB~143 tok/s ModelFit est.Q8_0 · 41 of 46 GB
- 13M4 Max · 48 GB · 40cMac · 48 GB~139 tok/s ModelFit est.Q4_K_M · 21 of 36 GB
- 142x RTX 3090Graphics card · 48 GB~136 tok/s ModelFit est.Q8_0 · 41 of 46 GB
- 15M5 Max · 36 GB · 32cMac · 36 GB~131 tok/s ModelFit est.Q4_K_M · 21 of 24 GB
- 162x RX 7900 XTXGraphics card · 48 GB~117 tok/s ModelFit est.Q8_0 · 41 of 46 GB
- 17M3 UltraMac · 96–512 GB · 5 variants~112 tok/s ModelFit est.Q8_0 · 41 GB
- 18M3 Max · 48 GB · 40cMac · 48 GB~111 tok/s ModelFit est.Q4_K_M · 21 of 36 GB
- 19M4 Max · 36 GB · 32cMac · 36 GB~110 tok/s ModelFit est.Q4_K_M · 21 of 24 GB
- 20M5 MaxMac · 64–128 GB · 2 variants~103 tok/s ModelFit est.Q8_0 · 41 GB
- 21M5 ProMac · 48 GB · 2 variants~101 tok/s ModelFit est.Q4_K_M · 21 GB
- 22M2 UltraMac · 64–192 GB · 7 variants~99 tok/s ModelFit est.Q8_0 · 41 GB
- 23M1 UltraMac · 64–128 GB · 4 variants~88 tok/s ModelFit est.Q8_0 · 41 GB
- 24M3 Max · 36 GB · 30cMac · 36 GB~87 tok/s ModelFit est.Q4_K_M · 21 of 24 GB
- 25M4 MaxMac · 64–128 GB · 2 variants~87 tok/s ModelFit est.Q8_0 · 41 GB
- 26M4 ProMac · 48 GB · 2 variants~85 tok/s ModelFit est.Q4_K_M · 21 GB
- 27M3 MaxMac · 64–128 GB · 2 variants~68 tok/s ModelFit est.Q8_0 · 41 GB
- 28M2 MaxMac · 64–96 GB · 3 variants~64 tok/s ModelFit est.Q8_0 · 41 GB
- 29M5 ProMac · 64 GB · 2 variants~60 tok/s ModelFit est.Q8_0 · 41 GB
- 30M1 MaxMac · 64 GB · 2 variants~57 tok/s ModelFit est.Q8_0 · 41 GB
- 31M3 Max · 96 GB · 30cMac · 96 GB~52 tok/s ModelFit est.Q8_0 · 41 of 72 GB
- 32M3 Pro · 36 GBMac · 36 GB~51 tok/s ModelFit est.Q4_K_M · 21 of 24 GB
- 33M4 ProMac · 64 GB · 2 variants~50 tok/s ModelFit est.Q8_0 · 41 GB
- 34DGX Spark (GB10)AI mini PC · 128 GB~45 tok/s our est.Q8_0 · 41 of 122 GB
- 35Ryzen AI Max+ 395 · 64 GBAI mini PC · 64 GB~42 tok/s our est.Q8_0 · 41 of 48 GB
- 36Ryzen AI Max+ 395 · 128 GBAI mini PC · 128 GB~40 tok/s ModelFit est.Q8_0 · 41 of 96 GB
Too big for 57 machines
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. Qwen3.5 35B-A3B Instruct needs about 21 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
About the model
- Parameters
- 35B
- Active per token
- 3B
- Type
- Mixture of experts
- Good for
- Reasoning, Coding, Agent scenarios
Builds and how to run them
| Quantization | Load | Min. RAM | Command |
|---|---|---|---|
| Q4_K_M | 20 GB | 32 GB | ollama run qwen3.5:35b-a3b |
| Q8_0 | 39 GB | 64 GB | ollama run qwen3.5:35b-a3b-q8_0 |
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 Qwen3.5 35B-A3B Instruct 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 M5 Max · 36 GB · 32c.
How much memory does Qwen3.5 35B-A3B Instruct need?
About 21 GB at the smallest build in our data, including a margin for the runtime and an 8K-token context. Longer contexts need more.
Does Qwen3.5 35B-A3B Instruct run on a DGX Spark?
Yes, at Q8_0. The Spark has 128 GB of unified memory, about 121.6 GB usable.