FitLocally by GPUwerk

SmolLM · 0.36B

Can you run SmolLM2 360M locally?

SmolLM2 360M is a 0.36B-parameter model. At 4-bit or better it runs on 120 of the 120 hardware configurations listed here; the smallest is the RTX 5060 (8 GB). On a 128 GB DGX Spark it runs at Q4_K_M.

Data as of 2 November 2026

Fastest machines for SmolLM2 360M

Every machine that runs it, fastest first. Filter by type; your machine is marked. Compare machines running it side by side

  1. 1RTX 5090Graphics card · 32 GB~523 tok/s ModelFit est.Q4_K_M · 1.5 of 31 GB
  2. 2RTX PRO 6000 BlackwellGraphics card · 96 GB~523 tok/s ModelFit est.Q4_K_M · 1.5 of 95 GB
  3. 32x RTX 5090Graphics card · 64 GB~453 tok/s ModelFit est.Q4_K_M · 1.5 of 62 GB
  4. 42x RTX PRO 6000 BlackwellGraphics card · 192 GB~453 tok/s ModelFit est.Q4_K_M · 1.5 of 190 GB
  5. 5RTX 4090Graphics card · 24 GB~420 tok/s ModelFit est.Q4_K_M · 1.5 of 23 GB
  6. 6RTX 5080Graphics card · 16 GB~419 tok/s ModelFit est.Q4_K_M · 1.5 of 15.0 GB
  7. 7RTX 5070 TiGraphics card · 16 GB~407 tok/s ModelFit est.Q4_K_M · 1.5 of 15.0 GB
  8. 8RTX 3090 TiGraphics card · 24 GB~376 tok/s ModelFit est.Q4_K_M · 1.5 of 23 GB
  9. 92x RTX 4090Graphics card · 48 GB~374 tok/s ModelFit est.Q4_K_M · 1.5 of 46 GB
  10. 10RTX 3090Graphics card · 24 GB~365 tok/s ModelFit est.Q4_K_M · 1.5 of 23 GB
  11. 11RTX 4080 SUPERGraphics card · 16 GB~363 tok/s ModelFit est.Q4_K_M · 1.5 of 15.0 GB
  12. 12RTX 4080Graphics card · 16 GB~358 tok/s ModelFit est.Q4_K_M · 1.5 of 15.0 GB
  13. 13RTX 5070Graphics card · 12 GB~354 tok/s ModelFit est.Q4_K_M · 1.5 of 11.0 GB
  14. 14M5 UltraMac · 96–512 GB · 5 variants~350 tok/s ModelFit est.Q4_K_M · 1.5 GB
  15. 15RTX 4070 Ti SUPERGraphics card · 16 GB~347 tok/s ModelFit est.Q4_K_M · 1.5 of 15.0 GB
  16. 162x RTX 3090 TiGraphics card · 48 GB~338 tok/s ModelFit est.Q4_K_M · 1.5 of 46 GB
  17. 17M5 MaxMac · 48–128 GB · 3 variants~336 tok/s ModelFit est.Q4_K_M · 1.5 GB
  18. 182x RTX 3090Graphics card · 48 GB~329 tok/s ModelFit est.Q4_K_M · 1.5 of 46 GB
  19. 19RTX 4070 TiGraphics card · 12 GB~295 tok/s ModelFit est.Q4_K_M · 1.5 of 11.0 GB
  20. 20RTX 4070 SUPERGraphics card · 12 GB~295 tok/s ModelFit est.Q4_K_M · 1.5 of 11.0 GB
  21. 21RTX 4070Graphics card · 12 GB~295 tok/s ModelFit est.Q4_K_M · 1.5 of 11.0 GB
  22. 22RTX 5060Graphics card · 8 GB~281 tok/s ModelFit est.Q4_K_M · 1.5 of 7.0 GB
  23. 23RTX 5060 TiGraphics card · 16 GB~281 tok/s ModelFit est.Q4_K_M · 1.5 of 15.0 GB
  24. 24M4 MaxMac · 48–128 GB · 3 variants~281 tok/s ModelFit est.Q4_K_M · 1.5 GB
  25. 25M5 Max · 36 GB · 32cMac · 36 GB~280 tok/s ModelFit est.Q4_K_M · 1.5 of 24 GB
  26. 26M3 UltraMac · 96–512 GB · 5 variants~265 tok/s ModelFit est.Q4_K_M · 1.5 GB
  27. 27RTX 3070Graphics card · 8 GB~250 tok/s ModelFit est.Q4_K_M · 1.5 of 7.0 GB
  28. 28RTX 3060 TiGraphics card · 8 GB~250 tok/s ModelFit est.Q4_K_M · 1.5 of 7.0 GB
  29. 29RX 7900 XTXGraphics card · 24 GB~249 tok/s ModelFit est.Q4_K_M · 1.5 of 23 GB
  30. 30RTX 2070Graphics card · 8 GB~242 tok/s ModelFit est.Q4_K_M · 1.5 of 7.0 GB
  31. 31RX 7900 XTGraphics card · 20 GB~236 tok/s ModelFit est.Q4_K_M · 1.5 of 19.0 GB
  32. 32M3 MaxMac · 48–128 GB · 3 variants~236 tok/s ModelFit est.Q4_K_M · 1.5 GB
  33. 33M4 Max · 36 GB · 32cMac · 36 GB~235 tok/s ModelFit est.Q4_K_M · 1.5 of 24 GB
  34. 34M5 ProMac · 24–64 GB · 6 variants~235 tok/s ModelFit est.Q4_K_M · 1.5 GB
  35. 352x RX 7900 XTXGraphics card · 48 GB~232 tok/s ModelFit est.Q4_K_M · 1.5 of 46 GB
  36. 36M2 UltraMac · 64–192 GB · 7 variants~218 tok/s ModelFit est.Q4_K_M · 1.5 GB
  37. 37RTX 3060Graphics card · 12 GB~217 tok/s ModelFit est.Q4_K_M · 1.5 of 11.0 GB
  38. 38RX 9070 XTGraphics card · 16 GB~210 tok/s ModelFit est.Q4_K_M · 1.5 of 15.0 GB
  39. 39M2 MaxMac · 32–96 GB · 5 variants~208 tok/s ModelFit est.Q4_K_M · 1.5 GB
  40. 40RTX 4060 TiGraphics card · 16 GB~201 tok/s ModelFit est.Q4_K_M · 1.5 of 15.0 GB
  41. 41M4 ProMac · 24–64 GB · 6 variants~197 tok/s ModelFit est.Q4_K_M · 1.5 GB
  42. 42M3 MaxMac · 36–96 GB · 2 variants~194 tok/s ModelFit est.Q4_K_M · 1.5 GB
  43. 43RTX 4060Graphics card · 8 GB~193 tok/s ModelFit est.Q4_K_M · 1.5 of 7.0 GB
  44. 44M1 UltraMac · 64–128 GB · 4 variants~192 tok/s ModelFit est.Q4_K_M · 1.5 GB
  45. 45Tesla P100Graphics card · 16 GB~188 tok/s ModelFit est.Q4_K_M · 1.5 of 15.0 GB
  46. 46M1 MaxMac · 32–64 GB · 4 variants~185 tok/s ModelFit est.Q4_K_M · 1.5 GB
  47. 47Tesla T4Graphics card · 16 GB~181 tok/s ModelFit est.Q4_K_M · 1.5 of 15.0 GB
  48. 48RX 9060 XTGraphics card · 16 GB~158 tok/s ModelFit est.Q4_K_M · 1.5 of 15.0 GB
  49. 49M6Mac · 24–32 GB · 3 variants~147 tok/s ModelFit est.Q4_K_M · 1.5 GB
  50. 50M2 ProMac · 16–32 GB · 2 variants~144 tok/s ModelFit est.Q4_K_M · 1.5 GB
  51. 51M6Mac · 16 GB · 2 variants~135 tok/s ModelFit est.Q4_K_M · 1.5 GB
  52. 52M5Mac · 16–32 GB · 6 variants~131 tok/s ModelFit est.Q4_K_M · 1.5 GB
  53. 53M1 ProMac · 16–32 GB · 2 variants~129 tok/s ModelFit est.Q4_K_M · 1.5 GB
  54. 54Ryzen AI Max+ 395 · 128 GBAI mini PC · 128 GB~129 tok/s ModelFit est.Q4_K_M · 1.5 of 96 GB
  55. 55M3 ProMac · 18–36 GB · 2 variants~124 tok/s ModelFit est.Q4_K_M · 1.5 GB
  56. 56M4Mac · 16–32 GB · 3 variants~98 tok/s ModelFit est.Q4_K_M · 1.5 GB
  57. 57M3Mac · 8–24 GB · 3 variants~86 tok/s ModelFit est.Q4_K_M · 1.5 GB
  58. 58M2Mac · 8–24 GB · 3 variants~81 tok/s ModelFit est.Q4_K_M · 1.5 GB
  59. 59M1Mac · 8–16 GB · 2 variants~52 tok/s ModelFit est.Q4_K_M · 1.5 GB
  60. 60Ryzen AI Max+ 395 · 64 GBAI mini PC · 64 GBno estimateQ4_K_M · 1.5 of 48 GB
  61. 61DGX Spark (GB10)AI mini PC · 128 GBno estimateQ4_K_M · 1.5 of 122 GB

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
0.36B
Active per token
not in our sources
Type
not in our sources
Good for
Chat, Embedded

Builds and how to run them

QuantizationLoadMin. RAMCommand
Q4_K_M0.5 GB1 GBollama run smollm2:360m

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 SmolLM2 360M 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 M3 · 8 GB.

How much memory does SmolLM2 360M need?

About 1.5 GB at the smallest build in our data, including a margin for the runtime and an 8K-token context. Longer contexts need more.

Does SmolLM2 360M run on a DGX Spark?

Yes, at Q4_K_M. The Spark has 128 GB of unified memory, about 121.6 GB usable.