DeepSeek · 70B
Can you run DeepSeek-R1 Distill Llama 70B locally?
DeepSeek-R1 Distill Llama 70B is a dense model with 70B parameters. At 4-bit or better it runs on 47 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 3.6 tokens per second (our est.).
Data as of 2 November 2026
Fastest machines for DeepSeek-R1 Distill Llama 70B
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~36 tok/s ModelFit est.Q4_K_M · 44 of 95 GB
- 22x RTX 5090Graphics card · 64 GB~36 tok/s ModelFit est.Q4_K_M · 44 of 62 GB
- 32x RTX PRO 6000 BlackwellGraphics card · 192 GB~36 tok/s ModelFit est.Q4_K_M · 44 of 190 GB
- 4M5 UltraMac · 96–512 GB · 5 variants~22 tok/s ModelFit est.Q4_K_M · 44 GB
- 5M3 UltraMac · 96–512 GB · 5 variants~15 tok/s ModelFit est.Q4_K_M · 44 GB
- 6M2 UltraMac · 64–192 GB · 7 variants~14 tok/s ModelFit est.Q4_K_M · 44 GB
- 72x RTX 4090Graphics card · 48 GB~13 tok/s our est.Q4_K_M · 44 of 46 GB
- 82x RTX 3090 TiGraphics card · 48 GB~13 tok/s our est.Q4_K_M · 44 of 46 GB
- 92x RX 7900 XTXGraphics card · 48 GB~13 tok/s our est.Q4_K_M · 44 of 46 GB
- 10M1 UltraMac · 64–128 GB · 4 variants~12 tok/s ModelFit est.Q4_K_M · 44 GB
- 112x RTX 3090Graphics card · 48 GB~12 tok/s our est.Q4_K_M · 44 of 46 GB
- 12M5 MaxMac · 64–128 GB · 2 variants~12 tok/s ModelFit est.Q4_K_M · 44 GB
- 13M4 MaxMac · 64–128 GB · 2 variants~9.7 tok/s slow ModelFit est.Q4_K_M · 44 GB
- 14M3 MaxMac · 64–128 GB · 2 variants~7.4 tok/s slow ModelFit est.Q4_K_M · 44 GB
- 15M2 MaxMac · 64–96 GB · 3 variants~7.1 tok/s slow ModelFit est.Q4_K_M · 44 GB
- 16M1 MaxMac · 64 GB · 2 variants~6.4 tok/s slow ModelFit est.Q4_K_M · 44 GB
- 17M5 ProMac · 64 GB · 2 variants~6.3 tok/s slow ModelFit est.Q4_K_M · 44 GB
- 18M3 Max · 96 GB · 30cMac · 96 GB~5.6 tok/s slow ModelFit est.Q4_K_M · 44 of 72 GB
- 19M4 ProMac · 64 GB · 2 variants~5.3 tok/s slow ModelFit est.Q4_K_M · 44 GB
- 20Ryzen AI Max+ 395 · 128 GBAI mini PC · 128 GB~4.5 tok/s slow ModelFit est.Q4_K_M · 44 of 96 GB
- 21DGX Spark (GB10)AI mini PC · 128 GB~3.6 tok/s slow our est.Q4_K_M · 44 of 122 GB
- 22Ryzen AI Max+ 395 · 64 GBAI mini PC · 64 GB~3.4 tok/s slow our est.Q4_K_M · 44 of 48 GB
Too big for 73 machines
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. DeepSeek-R1 Distill Llama 70B needs about 44 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
- 70B
- Active per token
- 70B
- Type
- Dense
- Good for
- Reasoning, Quality
Builds and how to run them
| Quantization | Load | Min. RAM | Command |
|---|---|---|---|
| Q4_K_M | 42 GB | 64 GB | ollama run deepseek-r1:70b |
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 DeepSeek-R1 Distill Llama 70B 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 M2 Ultra · 64 GB · 76c.
How much memory does DeepSeek-R1 Distill Llama 70B need?
About 44 GB at the smallest build in our data, including a margin for the runtime and an 8K-token context. Longer contexts need more.
Does DeepSeek-R1 Distill Llama 70B run on a DGX Spark?
Yes, at Q4_K_M. The Spark has 128 GB of unified memory, about 121.6 GB usable.