FitLocally by GPUwerk

Granite · 3B

Can you run Granite 4.1 3B Instruct locally?

Granite 4.1 3B Instruct is a 3B-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 Granite 4.1 3B Instruct

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~350 tok/s ModelFit est.Q4_K_M · 3.0 of 31 GB
  2. 2RTX PRO 6000 BlackwellGraphics card · 96 GB~350 tok/s ModelFit est.Q4_K_M · 3.0 of 95 GB
  3. 32x RTX 5090Graphics card · 64 GB~317 tok/s ModelFit est.Q4_K_M · 3.0 of 62 GB
  4. 42x RTX PRO 6000 BlackwellGraphics card · 192 GB~317 tok/s ModelFit est.Q4_K_M · 3.0 of 190 GB
  5. 5RTX 4090Graphics card · 24 GB~243 tok/s ModelFit est.Q4_K_M · 3.0 of 23 GB
  6. 6RTX 5080Graphics card · 16 GB~241 tok/s ModelFit est.Q4_K_M · 3.0 of 15.0 GB
  7. 7RTX 5070 TiGraphics card · 16 GB~230 tok/s ModelFit est.Q4_K_M · 3.0 of 15.0 GB
  8. 8M5 UltraMac · 96–512 GB · 5 variants~228 tok/s ModelFit est.Q4_K_M · 3.0 GB
  9. 92x RTX 4090Graphics card · 48 GB~226 tok/s ModelFit est.Q4_K_M · 3.0 of 46 GB
  10. 10RTX 3090 TiGraphics card · 24 GB~223 tok/s ModelFit est.Q4_K_M · 3.0 of 23 GB
  11. 11RTX 3090Graphics card · 24 GB~212 tok/s ModelFit est.Q4_K_M · 3.0 of 23 GB
  12. 122x RTX 3090 TiGraphics card · 48 GB~209 tok/s ModelFit est.Q4_K_M · 3.0 of 46 GB
  13. 132x RTX 3090Graphics card · 48 GB~200 tok/s ModelFit est.Q4_K_M · 3.0 of 46 GB
  14. 14RTX 4080 SUPERGraphics card · 16 GB~194 tok/s ModelFit est.Q4_K_M · 3.0 of 15.0 GB
  15. 15RTX 4080Graphics card · 16 GB~191 tok/s ModelFit est.Q4_K_M · 3.0 of 15.0 GB
  16. 16RTX 5070Graphics card · 12 GB~187 tok/s ModelFit est.Q4_K_M · 3.0 of 11.0 GB
  17. 17RTX 4070 Ti SUPERGraphics card · 16 GB~182 tok/s ModelFit est.Q4_K_M · 3.0 of 15.0 GB
  18. 18RX 7900 XTXGraphics card · 24 GB~168 tok/s ModelFit est.Q4_K_M · 3.0 of 23 GB
  19. 19M5 MaxMac · 48–128 GB · 3 variants~166 tok/s ModelFit est.Q4_K_M · 3.0 GB
  20. 20M3 UltraMac · 96–512 GB · 5 variants~164 tok/s ModelFit est.Q4_K_M · 3.0 GB
  21. 212x RX 7900 XTXGraphics card · 48 GB~160 tok/s ModelFit est.Q4_K_M · 3.0 of 46 GB
  22. 22RX 7900 XTGraphics card · 20 GB~153 tok/s ModelFit est.Q4_K_M · 3.0 of 19.0 GB
  23. 23RTX 4070 TiGraphics card · 12 GB~145 tok/s ModelFit est.Q4_K_M · 3.0 of 11.0 GB
  24. 24RTX 4070 SUPERGraphics card · 12 GB~145 tok/s ModelFit est.Q4_K_M · 3.0 of 11.0 GB
  25. 25RTX 4070Graphics card · 12 GB~145 tok/s ModelFit est.Q4_K_M · 3.0 of 11.0 GB
  26. 26M2 UltraMac · 64–192 GB · 7 variants~141 tok/s ModelFit est.Q4_K_M · 3.0 GB
  27. 27M4 MaxMac · 48–128 GB · 3 variants~139 tok/s ModelFit est.Q4_K_M · 3.0 GB
  28. 28RTX 5060Graphics card · 8 GB~137 tok/s ModelFit est.Q4_K_M · 3.0 of 7.0 GB
  29. 29RTX 5060 TiGraphics card · 16 GB~137 tok/s ModelFit est.Q4_K_M · 3.0 of 15.0 GB
  30. 30RX 9070 XTGraphics card · 16 GB~134 tok/s ModelFit est.Q4_K_M · 3.0 of 15.0 GB
  31. 31M5 Max · 36 GB · 32cMac · 36 GB~131 tok/s ModelFit est.Q4_K_M · 3.0 of 24 GB
  32. 32M1 UltraMac · 64–128 GB · 4 variants~125 tok/s ModelFit est.Q4_K_M · 3.0 GB
  33. 33RTX 3070Graphics card · 8 GB~121 tok/s ModelFit est.Q4_K_M · 3.0 of 7.0 GB
  34. 34RTX 3060 TiGraphics card · 8 GB~121 tok/s ModelFit est.Q4_K_M · 3.0 of 7.0 GB
  35. 35M3 MaxMac · 48–128 GB · 3 variants~111 tok/s ModelFit est.Q4_K_M · 3.0 GB
  36. 36RTX 2070Graphics card · 8 GB~111 tok/s ModelFit est.Q4_K_M · 3.0 of 7.0 GB
  37. 37M4 Max · 36 GB · 32cMac · 36 GB~110 tok/s ModelFit est.Q4_K_M · 3.0 of 24 GB
  38. 38M2 MaxMac · 32–96 GB · 5 variants~102 tok/s ModelFit est.Q4_K_M · 3.0 GB
  39. 39RTX 3060Graphics card · 12 GB~101 tok/s ModelFit est.Q4_K_M · 3.0 of 11.0 GB
  40. 40M5 ProMac · 24–64 GB · 6 variants~101 tok/s ModelFit est.Q4_K_M · 3.0 GB
  41. 41M1 MaxMac · 32–64 GB · 4 variants~92 tok/s ModelFit est.Q4_K_M · 3.0 GB
  42. 42RTX 4060 TiGraphics card · 16 GB~89 tok/s ModelFit est.Q4_K_M · 3.0 of 15.0 GB
  43. 43M3 MaxMac · 36–96 GB · 2 variants~87 tok/s ModelFit est.Q4_K_M · 3.0 GB
  44. 44Tesla P100Graphics card · 16 GB~87 tok/s ModelFit est.Q4_K_M · 3.0 of 15.0 GB
  45. 45RX 9060 XTGraphics card · 16 GB~85 tok/s ModelFit est.Q4_K_M · 3.0 of 15.0 GB
  46. 46M4 ProMac · 24–64 GB · 6 variants~85 tok/s ModelFit est.Q4_K_M · 3.0 GB
  47. 47RTX 4060Graphics card · 8 GB~84 tok/s ModelFit est.Q4_K_M · 3.0 of 7.0 GB
  48. 48Tesla T4Graphics card · 16 GB~78 tok/s ModelFit est.Q4_K_M · 3.0 of 15.0 GB
  49. 49Ryzen AI Max+ 395 · 128 GBAI mini PC · 128 GB~64 tok/s ModelFit est.Q4_K_M · 3.0 of 96 GB
  50. 50M2 ProMac · 16–32 GB · 2 variants~62 tok/s ModelFit est.Q4_K_M · 3.0 GB
  51. 51M6Mac · 24–32 GB · 3 variants~61 tok/s ModelFit est.Q4_K_M · 3.0 GB
  52. 52M1 ProMac · 16–32 GB · 2 variants~56 tok/s ModelFit est.Q4_K_M · 3.0 GB
  53. 53M6Mac · 16 GB · 2 variants~55 tok/s ModelFit est.Q4_K_M · 3.0 GB
  54. 54M5Mac · 16–32 GB · 6 variants~52 tok/s ModelFit est.Q4_K_M · 3.0 GB
  55. 55M3 ProMac · 18–36 GB · 2 variants~51 tok/s ModelFit est.Q4_K_M · 3.0 GB
  56. 56M4Mac · 16–32 GB · 3 variants~39 tok/s ModelFit est.Q4_K_M · 3.0 GB
  57. 57M3Mac · 8–24 GB · 3 variants~34 tok/s ModelFit est.Q4_K_M · 3.0 GB
  58. 58M2Mac · 8–24 GB · 3 variants~32 tok/s ModelFit est.Q4_K_M · 3.0 GB
  59. 59M1Mac · 8–16 GB · 2 variants~20 tok/s ModelFit est.Q4_K_M · 3.0 GB
  60. 60Ryzen AI Max+ 395 · 64 GBAI mini PC · 64 GBno estimateQ4_K_M · 3.0 of 48 GB
  61. 61DGX Spark (GB10)AI mini PC · 128 GBno estimateQ4_K_M · 3.0 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
3B
Active per token
not in our sources
Type
not in our sources
Good for
Lightweight chat, classification, edge tasks

Builds and how to run them

QuantizationLoadMin. RAMCommand
Q4_K_M2.0 GB4 GBollama run granite4.1:3b

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 Granite 4.1 3B Instruct 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 Granite 4.1 3B Instruct need?

About 3.0 GB at the smallest build in our data, including a margin for the runtime and an 8K-token context. Longer contexts need more.

Does Granite 4.1 3B Instruct run on a DGX Spark?

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