Flint · 39.8B · MoE
Can you run Flint 40B-A2.5B locally?
Flint 40B-A2.5B is a mixture-of-experts model with 39.8B parameters, 2.5B active per token. At 4-bit or better it runs on 55 of the 120 hardware configurations listed here; the smallest is the RTX 5090 (32 GB). On a 128 GB DGX Spark it runs at NVFP4, at roughly 104 tokens per second (our est.).
Data as of 2 November 2026
Fastest machines for Flint 40B-A2.5B
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~363 tok/s ModelFit est.NVFP4 · 24 of 31 GB
- 2RTX PRO 6000 BlackwellGraphics card · 96 GB~363 tok/s ModelFit est.NVFP4 · 24 of 95 GB
- 32x RTX 5090Graphics card · 64 GB~327 tok/s ModelFit est.NVFP4 · 24 of 62 GB
- 42x RTX PRO 6000 BlackwellGraphics card · 192 GB~327 tok/s ModelFit est.NVFP4 · 24 of 190 GB
- 5M5 UltraMac · 96–512 GB · 5 variants~236 tok/s ModelFit est.NVFP4 · 24 GB
- 62x RTX 4090Graphics card · 48 GB~236 tok/s ModelFit est.NVFP4 · 24 of 46 GB
- 72x RTX 3090 TiGraphics card · 48 GB~218 tok/s ModelFit est.NVFP4 · 24 of 46 GB
- 82x RTX 3090Graphics card · 48 GB~208 tok/s ModelFit est.NVFP4 · 24 of 46 GB
- 9M5 MaxMac · 48–128 GB · 3 variants~175 tok/s ModelFit est.NVFP4 · 24 GB
- 10M3 UltraMac · 96–512 GB · 5 variants~170 tok/s ModelFit est.NVFP4 · 24 GB
- 112x RX 7900 XTXGraphics card · 48 GB~166 tok/s ModelFit est.NVFP4 · 24 of 46 GB
- 12M4 MaxMac · 48–128 GB · 3 variants~147 tok/s ModelFit est.NVFP4 · 24 GB
- 13M2 UltraMac · 64–192 GB · 7 variants~146 tok/s ModelFit est.NVFP4 · 24 GB
- 14M1 UltraMac · 64–128 GB · 4 variants~130 tok/s ModelFit est.NVFP4 · 24 GB
- 15M3 MaxMac · 48–128 GB · 3 variants~118 tok/s ModelFit est.NVFP4 · 24 GB
- 16M2 MaxMac · 64–96 GB · 3 variants~108 tok/s ModelFit est.NVFP4 · 24 GB
- 17M5 ProMac · 48–64 GB · 4 variants~107 tok/s ModelFit est.NVFP4 · 24 GB
- 18DGX Spark (GB10)AI mini PC · 128 GB~104 tok/s our est.NVFP4 · 24 of 122 GB
- 19Ryzen AI Max+ 395 · 64 GBAI mini PC · 64 GB~98 tok/s our est.NVFP4 · 24 of 48 GB
- 20M1 MaxMac · 64 GB · 2 variants~97 tok/s ModelFit est.NVFP4 · 24 GB
- 21M3 Max · 96 GB · 30cMac · 96 GB~92 tok/s ModelFit est.NVFP4 · 24 of 72 GB
- 22M4 ProMac · 48–64 GB · 4 variants~90 tok/s ModelFit est.NVFP4 · 24 GB
- 23Ryzen AI Max+ 395 · 128 GBAI mini PC · 128 GB~68 tok/s ModelFit est.NVFP4 · 24 of 96 GB
Too big for 65 machines
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. Flint 40B-A2.5B needs about 24 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
- 39.8B
- Active per token
- 2.5B
- Type
- Mixture of experts
- Good for
- Agentic coding, Long context
Builds and how to run them
| Quantization | Load | Min. RAM | Command |
|---|---|---|---|
| NVFP4 | 23 GB | 36 GB | ollama run flint:40b |
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 Flint 40B-A2.5B 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 Flint 40B-A2.5B need?
About 24 GB at the smallest build in our data, including a margin for the runtime and an 8K-token context. Longer contexts need more.
Does Flint 40B-A2.5B run on a DGX Spark?
Yes, at NVFP4. The Spark has 128 GB of unified memory, about 121.6 GB usable.