Llama · 109B · MoE
Can you run Llama 4 Scout locally?
Llama 4 Scout is a mixture-of-experts model with 109B parameters, 17B active per token. At 4-bit or better it runs on 26 of the 120 hardware configurations listed here; the smallest is the RTX PRO 6000 Blackwell (96 GB). On a 128 GB DGX Spark it runs at Q4_K_M, at roughly 14 tokens per second (our est.).
Data as of 2 November 2026
Fastest machines for Llama 4 Scout
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~116 tok/s ModelFit est.Q4_K_M · 70 of 95 GB
- 22x RTX PRO 6000 BlackwellGraphics card · 192 GB~112 tok/s ModelFit est.Q4_K_M · 70 of 190 GB
- 3M5 UltraMac · 96–512 GB · 5 variants~73 tok/s ModelFit est.Q4_K_M · 70 GB
- 4M3 UltraMac · 96–512 GB · 5 variants~49 tok/s ModelFit est.Q4_K_M · 70 GB
- 5M2 UltraMac · 96–192 GB · 5 variants~45 tok/s ModelFit est.Q4_K_M · 70 GB
- 6M5 Max · 128 GB · 40cMac · 128 GB~41 tok/s ModelFit est.Q4_K_M · 70 of 96 GB
- 7M1 UltraMac · 128 GB · 2 variants~40 tok/s ModelFit est.Q4_K_M · 70 GB
- 8M4 Max · 128 GB · 40cMac · 128 GB~34 tok/s ModelFit est.Q4_K_M · 70 of 96 GB
- 9M3 Max · 128 GB · 40cMac · 128 GB~26 tok/s ModelFit est.Q4_K_M · 70 of 96 GB
- 10M2 Max · 96 GB · 38cMac · 96 GB~25 tok/s ModelFit est.Q4_K_M · 70 of 72 GB
- 11M3 Max · 96 GB · 30cMac · 96 GB~20 tok/s ModelFit est.Q4_K_M · 70 of 72 GB
- 12Ryzen AI Max+ 395 · 128 GBAI mini PC · 128 GB~16 tok/s ModelFit est.Q4_K_M · 70 of 96 GB
- 13DGX Spark (GB10)AI mini PC · 128 GB~14 tok/s our est.Q4_K_M · 70 of 122 GB
Too big for 94 machines
2x RTX 5090, Ryzen AI Max+ 395 · 64 GB, M2 Ultra · 64 GB · 76c, M2 Ultra · 64 GB · 60c, M1 Ultra · 64 GB · 64c, M1 Ultra · 64 GB · 48c, M5 Max · 64 GB · 40c, M4 Max · 64 GB · 40c, M3 Max · 64 GB · 40c, M2 Max · 64 GB · 38c, M2 Max · 64 GB · 30c, M1 Max · 64 GB · 32c, M1 Max · 64 GB · 24c, M5 Pro · 64 GB · 20c, M5 Pro · 64 GB · 16c, M4 Pro · 64 GB · 20c, M4 Pro · 64 GB · 16c, 2x RTX 4090, 2x RTX 3090 Ti, 2x RTX 3090, 2x RX 7900 XTX, M5 Max · 48 GB · 40c, M4 Max · 48 GB · 40c, M3 Max · 48 GB · 40c, M5 Pro · 48 GB · 20c, M5 Pro · 48 GB · 16c, M4 Pro · 48 GB · 20c, M4 Pro · 48 GB · 16c, 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. Llama 4 Scout needs about 70 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
- 109B
- Active per token
- 17B
- Type
- Mixture of experts
- Good for
- Long context, Quality, Multimodal
Builds and how to run them
| Quantization | Load | Min. RAM | Command |
|---|---|---|---|
| Q4_K_M | 67 GB | 96 GB | ollama run llama4:scout |
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 Llama 4 Scout 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 Ultra · 96 GB · 80c.
How much memory does Llama 4 Scout need?
About 70 GB at the smallest build in our data, including a margin for the runtime and an 8K-token context. Longer contexts need more.
Does Llama 4 Scout run on a DGX Spark?
Yes, at Q4_K_M. The Spark has 128 GB of unified memory, about 121.6 GB usable.