Mistral · 46.7B · MoE
Can you run Mixtral 8x7B Instruct locally?
Mixtral 8x7B Instruct is a mixture-of-experts model with 46.7B parameters, 12.9B active per token. At 4-bit or better it runs on 54 of the 120 hardware configurations listed here; the smallest is the 2x RTX 4090 (48 GB). On a 128 GB DGX Spark it runs at Q4_K_M, at roughly 18 tokens per second (our est.).
Data as of 2 November 2026
Fastest machines for Mixtral 8x7B Instruct
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~111 tok/s ModelFit est.Q4_K_M · 32 of 95 GB
- 22x RTX 5090Graphics card · 64 GB~108 tok/s ModelFit est.Q4_K_M · 32 of 62 GB
- 32x RTX PRO 6000 BlackwellGraphics card · 192 GB~108 tok/s ModelFit est.Q4_K_M · 32 of 190 GB
- 4M5 UltraMac · 96–512 GB · 5 variants~70 tok/s ModelFit est.Q4_K_M · 32 GB
- 52x RTX 4090Graphics card · 48 GB~63 tok/s ModelFit est.Q4_K_M · 32 of 46 GB
- 62x RTX 3090 TiGraphics card · 48 GB~60 tok/s ModelFit est.Q4_K_M · 32 of 46 GB
- 72x RTX 3090Graphics card · 48 GB~56 tok/s ModelFit est.Q4_K_M · 32 of 46 GB
- 82x RX 7900 XTXGraphics card · 48 GB~54 tok/s ModelFit est.Q4_K_M · 32 of 46 GB
- 9M3 UltraMac · 96–512 GB · 5 variants~47 tok/s ModelFit est.Q4_K_M · 32 GB
- 10M2 UltraMac · 64–192 GB · 7 variants~43 tok/s ModelFit est.Q4_K_M · 32 GB
- 11M5 MaxMac · 48–128 GB · 3 variants~39 tok/s ModelFit est.Q4_K_M · 32 GB
- 12M1 UltraMac · 64–128 GB · 4 variants~38 tok/s ModelFit est.Q4_K_M · 32 GB
- 13M4 MaxMac · 48–128 GB · 3 variants~33 tok/s ModelFit est.Q4_K_M · 32 GB
- 14M3 MaxMac · 48–128 GB · 3 variants~25 tok/s ModelFit est.Q4_K_M · 32 GB
- 15M2 MaxMac · 64–96 GB · 3 variants~24 tok/s ModelFit est.Q4_K_M · 32 GB
- 16M5 ProMac · 48–64 GB · 4 variants~22 tok/s ModelFit est.Q4_K_M · 32 GB
- 17M1 MaxMac · 64 GB · 2 variants~21 tok/s ModelFit est.Q4_K_M · 32 GB
- 18M3 Max · 96 GB · 30cMac · 96 GB~19 tok/s ModelFit est.Q4_K_M · 32 of 72 GB
- 19DGX Spark (GB10)AI mini PC · 128 GB~18 tok/s our est.Q4_K_M · 32 of 122 GB
- 20M4 ProMac · 48–64 GB · 4 variants~18 tok/s ModelFit est.Q4_K_M · 32 GB
- 21Ryzen AI Max+ 395 · 64 GBAI mini PC · 64 GB~17 tok/s our est.Q4_K_M · 32 of 48 GB
- 22Ryzen AI Max+ 395 · 128 GBAI mini PC · 128 GB~15 tok/s ModelFit est.Q4_K_M · 32 of 96 GB
Too big for 66 machines
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. Mixtral 8x7B Instruct needs about 32 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
- 46.7B
- Active per token
- 12.9B
- Type
- Mixture of experts
- Good for
- Coding, Quality
Builds and how to run them
| Quantization | Load | Min. RAM | Command |
|---|---|---|---|
| Q4_K_M | 30 GB | 48 GB | ollama run mixtral:8x7b |
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 Mixtral 8x7B 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 · 48 GB · 40c.
How much memory does Mixtral 8x7B Instruct need?
About 32 GB at the smallest build in our data, including a margin for the runtime and an 8K-token context. Longer contexts need more.
Does Mixtral 8x7B Instruct run on a DGX Spark?
Yes, at Q4_K_M. The Spark has 128 GB of unified memory, about 121.6 GB usable.