FitLocally by GPUwerk

LFM3 · 1.73B

Can you run LFM3 1.7B locally?

LFM3 1.7B is a 1.73B-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 LFM3 1.7B

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~484 tok/s ModelFit est.Q4_K_M · 2.1 of 31 GB
  2. 2RTX PRO 6000 BlackwellGraphics card · 96 GB~484 tok/s ModelFit est.Q4_K_M · 2.1 of 95 GB
  3. 32x RTX 5090Graphics card · 64 GB~423 tok/s ModelFit est.Q4_K_M · 2.1 of 62 GB
  4. 42x RTX PRO 6000 BlackwellGraphics card · 192 GB~423 tok/s ModelFit est.Q4_K_M · 2.1 of 190 GB
  5. 5RTX 4090Graphics card · 24 GB~375 tok/s ModelFit est.Q4_K_M · 2.1 of 23 GB
  6. 6RTX 5080Graphics card · 16 GB~374 tok/s ModelFit est.Q4_K_M · 2.1 of 15.0 GB
  7. 7RTX 5070 TiGraphics card · 16 GB~361 tok/s ModelFit est.Q4_K_M · 2.1 of 15.0 GB
  8. 8RTX 3090 TiGraphics card · 24 GB~338 tok/s ModelFit est.Q4_K_M · 2.1 of 23 GB
  9. 92x RTX 4090Graphics card · 48 GB~337 tok/s ModelFit est.Q4_K_M · 2.1 of 46 GB
  10. 10RTX 3090Graphics card · 24 GB~326 tok/s ModelFit est.Q4_K_M · 2.1 of 23 GB
  11. 11M5 UltraMac · 96–512 GB · 5 variants~322 tok/s ModelFit est.Q4_K_M · 2.1 GB
  12. 12RTX 4080 SUPERGraphics card · 16 GB~318 tok/s ModelFit est.Q4_K_M · 2.1 of 15.0 GB
  13. 13RTX 4080Graphics card · 16 GB~313 tok/s ModelFit est.Q4_K_M · 2.1 of 15.0 GB
  14. 14RTX 5070Graphics card · 12 GB~309 tok/s ModelFit est.Q4_K_M · 2.1 of 11.0 GB
  15. 152x RTX 3090 TiGraphics card · 48 GB~307 tok/s ModelFit est.Q4_K_M · 2.1 of 46 GB
  16. 16RTX 4070 Ti SUPERGraphics card · 16 GB~302 tok/s ModelFit est.Q4_K_M · 2.1 of 15.0 GB
  17. 172x RTX 3090Graphics card · 48 GB~297 tok/s ModelFit est.Q4_K_M · 2.1 of 46 GB
  18. 18M5 MaxMac · 48–128 GB · 3 variants~288 tok/s ModelFit est.Q4_K_M · 2.1 GB
  19. 19RTX 4070 TiGraphics card · 12 GB~252 tok/s ModelFit est.Q4_K_M · 2.1 of 11.0 GB
  20. 20RTX 4070 SUPERGraphics card · 12 GB~252 tok/s ModelFit est.Q4_K_M · 2.1 of 11.0 GB
  21. 21RTX 4070Graphics card · 12 GB~252 tok/s ModelFit est.Q4_K_M · 2.1 of 11.0 GB
  22. 22M4 MaxMac · 48–128 GB · 3 variants~241 tok/s ModelFit est.Q4_K_M · 2.1 GB
  23. 23M3 UltraMac · 96–512 GB · 5 variants~241 tok/s ModelFit est.Q4_K_M · 2.1 GB
  24. 24RTX 5060Graphics card · 8 GB~240 tok/s ModelFit est.Q4_K_M · 2.1 of 7.0 GB
  25. 25RTX 5060 TiGraphics card · 16 GB~240 tok/s ModelFit est.Q4_K_M · 2.1 of 15.0 GB
  26. 26M5 Max · 36 GB · 32cMac · 36 GB~236 tok/s ModelFit est.Q4_K_M · 2.1 of 24 GB
  27. 27RX 7900 XTXGraphics card · 24 GB~231 tok/s ModelFit est.Q4_K_M · 2.1 of 23 GB
  28. 28RX 7900 XTGraphics card · 20 GB~216 tok/s ModelFit est.Q4_K_M · 2.1 of 19.0 GB
  29. 292x RX 7900 XTXGraphics card · 48 GB~216 tok/s ModelFit est.Q4_K_M · 2.1 of 46 GB
  30. 30RTX 3070Graphics card · 8 GB~213 tok/s ModelFit est.Q4_K_M · 2.1 of 7.0 GB
  31. 31RTX 3060 TiGraphics card · 8 GB~213 tok/s ModelFit est.Q4_K_M · 2.1 of 7.0 GB
  32. 32RTX 2070Graphics card · 8 GB~203 tok/s ModelFit est.Q4_K_M · 2.1 of 7.0 GB
  33. 33M2 UltraMac · 64–192 GB · 7 variants~200 tok/s ModelFit est.Q4_K_M · 2.1 GB
  34. 34M3 MaxMac · 48–128 GB · 3 variants~199 tok/s ModelFit est.Q4_K_M · 2.1 GB
  35. 35M4 Max · 36 GB · 32cMac · 36 GB~198 tok/s ModelFit est.Q4_K_M · 2.1 of 24 GB
  36. 36M5 ProMac · 24–64 GB · 6 variants~193 tok/s ModelFit est.Q4_K_M · 2.1 GB
  37. 37RX 9070 XTGraphics card · 16 GB~192 tok/s ModelFit est.Q4_K_M · 2.1 of 15.0 GB
  38. 38RTX 3060Graphics card · 12 GB~183 tok/s ModelFit est.Q4_K_M · 2.1 of 11.0 GB
  39. 39M2 MaxMac · 32–96 GB · 5 variants~178 tok/s ModelFit est.Q4_K_M · 2.1 GB
  40. 40M1 UltraMac · 64–128 GB · 4 variants~177 tok/s ModelFit est.Q4_K_M · 2.1 GB
  41. 41RTX 4060 TiGraphics card · 16 GB~166 tok/s ModelFit est.Q4_K_M · 2.1 of 15.0 GB
  42. 42M4 ProMac · 24–64 GB · 6 variants~162 tok/s ModelFit est.Q4_K_M · 2.1 GB
  43. 43M3 MaxMac · 36–96 GB · 2 variants~161 tok/s ModelFit est.Q4_K_M · 2.1 GB
  44. 44RTX 4060Graphics card · 8 GB~159 tok/s ModelFit est.Q4_K_M · 2.1 of 7.0 GB
  45. 45M1 MaxMac · 32–64 GB · 4 variants~159 tok/s ModelFit est.Q4_K_M · 2.1 GB
  46. 46Tesla P100Graphics card · 16 GB~157 tok/s ModelFit est.Q4_K_M · 2.1 of 15.0 GB
  47. 47Tesla T4Graphics card · 16 GB~148 tok/s ModelFit est.Q4_K_M · 2.1 of 15.0 GB
  48. 48RX 9060 XTGraphics card · 16 GB~139 tok/s ModelFit est.Q4_K_M · 2.1 of 15.0 GB
  49. 49M6Mac · 24–32 GB · 3 variants~119 tok/s ModelFit est.Q4_K_M · 2.1 GB
  50. 50M2 ProMac · 16–32 GB · 2 variants~119 tok/s ModelFit est.Q4_K_M · 2.1 GB
  51. 51Ryzen AI Max+ 395 · 128 GBAI mini PC · 128 GB~111 tok/s ModelFit est.Q4_K_M · 2.1 of 96 GB
  52. 52M6Mac · 16 GB · 2 variants~109 tok/s ModelFit est.Q4_K_M · 2.1 GB
  53. 53M1 ProMac · 16–32 GB · 2 variants~106 tok/s ModelFit est.Q4_K_M · 2.1 GB
  54. 54M5Mac · 16–32 GB · 6 variants~105 tok/s ModelFit est.Q4_K_M · 2.1 GB
  55. 55M3 ProMac · 18–36 GB · 2 variants~100 tok/s ModelFit est.Q4_K_M · 2.1 GB
  56. 56M4Mac · 16–32 GB · 3 variants~79 tok/s ModelFit est.Q4_K_M · 2.1 GB
  57. 57M3Mac · 8–24 GB · 3 variants~69 tok/s ModelFit est.Q4_K_M · 2.1 GB
  58. 58M2Mac · 8–24 GB · 3 variants~65 tok/s ModelFit est.Q4_K_M · 2.1 GB
  59. 59M1Mac · 8–16 GB · 2 variants~41 tok/s ModelFit est.Q4_K_M · 2.1 GB
  60. 60Ryzen AI Max+ 395 · 64 GBAI mini PC · 64 GBno estimateQ4_K_M · 2.1 of 48 GB
  61. 61DGX Spark (GB10)AI mini PC · 128 GBno estimateQ4_K_M · 2.1 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
1.73B
Active per token
not in our sources
Type
not in our sources
Good for
Local agents, Tool calling, Structured output

Builds and how to run them

QuantizationLoadMin. RAMCommand
Q4_K_M1.1 GB4 GBollama run lfm3:1.7b

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 LFM3 1.7B 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 LFM3 1.7B need?

About 2.1 GB at the smallest build in our data, including a margin for the runtime and an 8K-token context. Longer contexts need more.

Does LFM3 1.7B run on a DGX Spark?

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