model family

Granite 4.0

Published by ibm-granite. 1 member measured on real machines, across 1 build. Every number below was signed by the machine that produced it — none of it is from a model card.

what it takes, what it returns
text → text

Declared by the network’s catalog, not measured — a signature says what this family would be asked. Whether it answered is the signed capability flags on each member.

1 of 103 builds measured · 102 still open
Granite 4.0 1B1 build measured →
hf.co/ibm-granite/granite-4.0-1b-GGUF:Q4_K_M1b · Q4_K_M · ibm-granite · ollama · 1 machine · 1.63B
4,096recalled
—served
11.1best tok/s
recalled 4k⌐ declared 128k · unsignedadvertises 32× what it proved

Builds this network knows of

Declared, not measured — this is what the catalog says exists and what it would cost a machine to hold. Nothing here is signed, and none of it claims the build works.

how much memory does your machine have

100 of 103 builds fit a 16 GB machine — budgeting 70% of it, or 11.2 GiB, because the cache and the runtime want the rest.

  • hf.co/ibm-granite/granite-4.0-h-350m-GGUF:Q2_KQ2_Kollamapublished by ibm-granite
    0.1 GiB
  • hf.co/taronaeo/Granite-4.0-H-350M-BE-GGUF:Q2_KQ2_Kollamaderived by taronaeo
    0.1 GiB
  • hf.co/unsloth/granite-4.0-350m-GGUF:IQ3_XXSIQ3_XXSollamaquantized by unsloth
    0.2 GiB
  • hf.co/taronaeo/Granite-4.0-350M-BE-GGUF:Q2_KQ2_Kollamaderived by taronaeo
    0.2 GiB
  • hf.co/ibm-granite/granite-4.0-h-350m-GGUF:Q3_K_SQ3_K_Sollamapublished by ibm-granite
    0.2 GiB
  • hf.co/taronaeo/Granite-4.0-H-350M-BE-GGUF:Q3_K_SQ3_K_Sollamaderived by taronaeo
    0.2 GiB
  • hf.co/ibm-granite/granite-4.0-h-350m-GGUF:Q3_K_LQ3_K_Lollamapublished by ibm-granite
    0.2 GiB
  • hf.co/taronaeo/Granite-4.0-H-350M-BE-GGUF:Q3_K_LQ3_K_Lollamaderived by taronaeo
    0.2 GiB
  • hf.co/taronaeo/Granite-4.0-350M-BE-GGUF:Q3_K_SQ3_K_Sollamaderived by taronaeo
    0.2 GiB
  • hf.co/ibm-granite/granite-4.0-h-350m-GGUF:Q4_0Q4_0ollamapublished by ibm-granite
    0.2 GiB
  • hf.co/ibm-granite/granite-4.0-h-350m-GGUF:Q4_K_SQ4_K_Sollamapublished by ibm-granite
    0.2 GiB
  • hf.co/taronaeo/Granite-4.0-H-350M-BE-GGUF:Q4_0Q4_0ollamaderived by taronaeo
    0.2 GiB
  • hf.co/taronaeo/Granite-4.0-H-350M-BE-GGUF:Q4_K_SQ4_K_Sollamaderived by taronaeo
    0.2 GiB
  • hf.co/taronaeo/Granite-4.0-350M-BE-GGUF:Q3_K_LQ3_K_Lollamaderived by taronaeo
    0.2 GiB
  • hf.co/unsloth/granite-4.0-350m-GGUF:IQ4_XSIQ4_XSollamaquantized by unsloth
    0.2 GiB
  • hf.co/ibm-granite/granite-4.0-h-350m-GGUF:Q4_K_MQ4_K_Mollamapublished by ibm-granite
    0.2 GiB
  • hf.co/taronaeo/Granite-4.0-H-350M-BE-GGUF:Q4_K_MQ4_K_Mollamaderived by taronaeo
    0.2 GiB
  • hf.co/taronaeo/Granite-4.0-350M-BE-GGUF:Q4_0Q4_0ollamaderived by taronaeo
    0.2 GiB
  • hf.co/unsloth/granite-4.0-350m-GGUF:Q4_0Q4_0ollamaquantized by unsloth
    0.2 GiB
  • hf.co/unsloth/granite-4.0-350m-GGUF:Q4_K_SQ4_K_Sollamaquantized by unsloth
    0.2 GiB
  • hf.co/unsloth/granite-4.0-350m-GGUF:Q4_K_MQ4_K_Mollamaquantized by unsloth
    0.2 GiB
  • hf.co/taronaeo/Granite-4.0-350M-BE-GGUF:Q4_K_MQ4_K_Mollamaderived by taronaeo
    0.2 GiB
  • mlx-community/granite-4.0-h-350m-8bit8BITmlxquantized by mlx-community
    0.3 GiB
  • hf.co/ibm-granite/granite-4.0-h-350m-GGUF:Q8_0Q8_0ollamapublished by ibm-granite
    0.3 GiB
  • hf.co/taronaeo/Granite-4.0-H-350M-BE-GGUF:Q8_0Q8_0ollamaderived by taronaeo
    0.3 GiB
  • hf.co/unsloth/granite-4.0-350m-GGUF:Q8_0Q8_0ollamaquantized by unsloth
    0.4 GiB
  • hf.co/taronaeo/Granite-4.0-350M-BE-GGUF:Q8_0Q8_0ollamaderived by taronaeo
    0.4 GiB
  • hf.co/ibm-granite/granite-4.0-h-1b-GGUF:Q2_KQ2_Kollamapublished by ibm-granite
    0.5 GiB
  • hf.co/ibm-granite/granite-4.0-h-1b-base-GGUF:Q2_KQ2_Kollamapublished by ibm-granite
    0.5 GiB
  • ibm-granite/granite-4.0-h-350m-baseBF16vllmpublished by ibm-granite
    0.6 GiB
  • hf.co/ibm-granite/granite-4.0-h-350m-GGUF:BF16BF16ollamapublished by ibm-granite
    0.6 GiB
  • hf.co/taronaeo/Granite-4.0-H-350M-BE-GGUF:BF16BF16ollamaderived by taronaeo
    0.6 GiB
  • hf.co/taronaeo/Granite-4.0-H-350M-BE-GGUF:F16F16ollamaderived by taronaeo
    0.6 GiB
  • hf.co/ibm-granite/granite-4.0-h-1b-GGUF:Q3_K_SQ3_K_Sollamapublished by ibm-granite
    0.6 GiB
  • hf.co/ibm-granite/granite-4.0-h-1b-base-GGUF:Q3_K_SQ3_K_Sollamapublished by ibm-granite
    0.6 GiB
  • hf.co/ibm-granite/granite-4.0-1b-GGUF:Q2_KQ2_Kollamapublished by ibm-granite
    0.7 GiB
  • hf.co/ibm-granite/granite-4.0-1b-base-GGUF:Q2_KQ2_Kollamapublished by ibm-granite
    0.7 GiB
  • hf.co/taronaeo/Granite-4.0-1B-BE-GGUF:Q2_KQ2_Kollamaderived by taronaeo
    0.7 GiB
  • ibm-granite/granite-4.0-350mBF16vllmpublished by ibm-granite
    0.7 GiB
  • ibm-granite/granite-4.0-350m-baseBF16vllmpublished by ibm-granite
    0.7 GiB
  • unsloth/granite-4.0-350mBF16vllmderived by unsloth
    0.7 GiB
  • hf.co/unsloth/granite-4.0-350m-GGUF:BF16BF16ollamaquantized by unsloth
    0.7 GiB
  • hf.co/taronaeo/Granite-4.0-350M-BE-GGUF:F16F16ollamaderived by taronaeo
    0.7 GiB
  • hf.co/taronaeo/Granite-4.0-350M-BE-GGUF:BF16BF16ollamaderived by taronaeo
    0.7 GiB
  • hf.co/ibm-granite/granite-4.0-h-1b-GGUF:Q3_K_LQ3_K_Lollamapublished by ibm-granite
    0.7 GiB
  • hf.co/ibm-granite/granite-4.0-h-1b-base-GGUF:Q3_K_LQ3_K_Lollamapublished by ibm-granite
    0.7 GiB
  • hf.co/unsloth/granite-4.0-h-micro-GGUF:IQ1_SIQ1_Sollamaquantized by unsloth
    0.7 GiB
  • hf.co/ibm-granite/granite-4.0-1b-GGUF:Q3_K_SQ3_K_Sollamapublished by ibm-granite
    0.7 GiB
  • hf.co/ibm-granite/granite-4.0-1b-base-GGUF:Q3_K_SQ3_K_Sollamapublished by ibm-granite
    0.7 GiB
  • hf.co/taronaeo/Granite-4.0-1B-BE-GGUF:Q3_K_SQ3_K_Sollamaderived by taronaeo
    0.7 GiB
  • mlx-community/granite-4.0-h-1b-4bit4BITmlxquantized by mlx-community
    0.8 GiB
  • hf.co/ibm-granite/granite-4.0-h-1b-GGUF:Q4_0Q4_0ollamapublished by ibm-granite
    0.8 GiB
  • hf.co/ibm-granite/granite-4.0-h-1b-base-GGUF:Q4_0Q4_0ollamapublished by ibm-granite
    0.8 GiB
  • hf.co/ibm-granite/granite-4.0-h-1b-GGUF:Q4_K_MQ4_K_Mollamapublished by ibm-granite
    0.8 GiB
  • hf.co/ibm-granite/granite-4.0-h-1b-base-GGUF:Q4_K_MQ4_K_Mollamapublished by ibm-granite
    0.8 GiB
  • hf.co/ibm-granite/granite-4.0-1b-GGUF:Q3_K_LQ3_K_Lollamapublished by ibm-granite
    0.9 GiB
  • hf.co/ibm-granite/granite-4.0-1b-base-GGUF:Q3_K_LQ3_K_Lollamapublished by ibm-granite
    0.9 GiB
  • hf.co/taronaeo/Granite-4.0-1B-BE-GGUF:Q3_K_LQ3_K_Lollamaderived by taronaeo
    0.9 GiB
  • hf.co/unsloth/granite-4.0-h-micro-GGUF:IQ2_XXSIQ2_XXSollamaquantized by unsloth
    0.9 GiB
  • hf.co/ibm-granite/granite-4.0-1b-GGUF:Q4_0Q4_0ollamapublished by ibm-granite
    0.9 GiB
  • hf.co/ibm-granite/granite-4.0-1b-base-GGUF:Q4_0Q4_0ollamapublished by ibm-granite
    0.9 GiB
  • hf.co/taronaeo/Granite-4.0-1B-BE-GGUF:Q4_0Q4_0ollamaderived by taronaeo
    0.9 GiB
  • hf.co/ibm-granite/granite-4.0-1b-GGUF:Q4_K_MQ4_K_Mollamameasured herepublished by ibm-granite
    1.0 GiB
  • hf.co/ibm-granite/granite-4.0-1b-base-GGUF:Q4_K_MQ4_K_Mollamapublished by ibm-granite
    1.0 GiB
  • hf.co/taronaeo/Granite-4.0-1B-BE-GGUF:Q4_K_MQ4_K_Mollamaderived by taronaeo
    1.0 GiB
  • hf.co/ibm-granite/granite-4.0-1b-speech-GGUF:Q4_K_MQ4_K_Mollamapublished by ibm-granite
    1.1 GiB
  • mlx-community/granite-4.0-h-1b-6bit6BITmlxquantized by mlx-community
    1.1 GiB
  • hf.co/unsloth/granite-4.0-h-micro-GGUF:IQ3_XXSIQ3_XXSollamaquantized by unsloth
    1.2 GiB
  • hf.co/ibm-granite/granite-4.0-1b-speech-GGUF:Q5_K_MQ5_K_Mollamapublished by ibm-granite
    1.2 GiB
  • hf.co/ibm-granite/granite-4.0-h-1b-GGUF:Q8_0Q8_0ollamapublished by ibm-granite
    1.5 GiB
  • hf.co/ibm-granite/granite-4.0-h-1b-base-GGUF:Q8_0Q8_0ollamapublished by ibm-granite
    1.5 GiB
  • hf.co/ibm-granite/granite-4.0-1b-GGUF:Q8_0Q8_0ollamapublished by ibm-granite
    1.6 GiB
  • hf.co/ibm-granite/granite-4.0-1b-base-GGUF:Q8_0Q8_0ollamapublished by ibm-granite
    1.6 GiB
  • hf.co/taronaeo/Granite-4.0-1B-BE-GGUF:Q8_0Q8_0ollamaderived by taronaeo
    1.6 GiB
  • mlx-community/granite-4.0-h-micro-4bit4BITmlxquantized by mlx-community
    1.7 GiB
  • hf.co/unsloth/granite-4.0-h-micro-GGUF:Q4_0Q4_0ollamaquantized by unsloth
    1.7 GiB
  • hf.co/unsloth/granite-4.0-h-micro-GGUF:Q4_K_MQ4_K_Mollamaquantized by unsloth
    1.8 GiB
  • hf.co/ibm-granite/granite-4.0-1b-speech-GGUF:Q8_0Q8_0ollamapublished by ibm-granite
    1.8 GiB
  • unsloth/granite-4.0-micro-unsloth-bnb-4bitBITSANDBYTESvllmderived by unsloth
    2.4 GiB
  • hf.co/ibm-granite/granite-4.0-h-1b-GGUF:BF16BF16ollamapublished by ibm-granite
    2.7 GiB
  • hf.co/ibm-granite/granite-4.0-h-1b-base-GGUF:BF16BF16ollamapublished by ibm-granite
    2.7 GiB
  • ibm-granite/granite-4.0-1bBF16vllmpublished by ibm-granite
    3.0 GiB
  • ibm-granite/granite-4.0-1b-baseBF16vllmpublished by ibm-granite
    3.0 GiB
  • unsloth/granite-4.0-1bBF16vllmderived by unsloth
    3.0 GiB
  • hf.co/ibm-granite/granite-4.0-1b-GGUF:BF16BF16ollamapublished by ibm-granite
    3.0 GiB
  • hf.co/ibm-granite/granite-4.0-1b-base-GGUF:BF16BF16ollamapublished by ibm-granite
    3.0 GiB
  • hf.co/taronaeo/Granite-4.0-1B-BE-GGUF:BF16BF16ollamaderived by taronaeo
    3.0 GiB
  • hf.co/taronaeo/Granite-4.0-1B-BE-GGUF:F16F16ollamaderived by taronaeo
    3.0 GiB
  • hf.co/unsloth/granite-4.0-h-micro-GGUF:Q8_0Q8_0ollamaquantized by unsloth
    3.2 GiB
  • hf.co/ibm-granite/granite-4.0-1b-speech-GGUF:BF16BF16ollamapublished by ibm-granite
    3.4 GiB
  • mlx-community/granite-4.0-h-tiny-4bit4BITmlxderived by mlx-community
    3.6 GiB
  • lmstudio-community/granite-4.0-h-tiny-MLX-4bit4BITmlxquantized by lmstudio-community
    3.6 GiB
  • mlx-community/Granite-4.0-H-Tiny-4bit-DWQ4BITmlxderived by mlx-community
    3.6 GiB
  • ibm-granite/granite-4.0-1b-speechBF16vllmpublished by ibm-granite
    4.3 GiB
  • lmstudio-community/granite-4.0-h-tiny-MLX-6bit6BITmlxquantized by lmstudio-community
    5.3 GiB
  • hf.co/unsloth/granite-4.0-h-micro-GGUF:BF16BF16ollamaquantized by unsloth
    5.9 GiB
  • ibm-granite/granite-guardian-4.0-3b-toxicity-jaBF16vllmpublished by ibm-granite
    6.3 GiB
  • RedHatAI/granite-4.0-h-tiny-FP8-dynamicFP8vllmquantized by RedHatAI
    6.6 GiB
  • lmstudio-community/granite-4.0-h-tiny-MLX-8bit8BITmlxquantized by lmstudio-community
    6.9 GiB
  • ibm-granite/granite-4.0-3b-visionBF16vllmpublished by ibm-granite
    8.8 GiB
  • lmstudio-community/granite-4.0-h-small-MLX-4bit4BITmlxquantized by lmstudio-community
    16.9 GiB
  • lmstudio-community/granite-4.0-h-small-MLX-6bit6BITmlxquantized by lmstudio-community
    24.4 GiB
  • lmstudio-community/granite-4.0-h-small-MLX-8bit8BITmlxquantized by lmstudio-community
    31.9 GiB

Sizes are what the catalog declares, not what a machine measured — fitting on disk is necessary and not sufficient. Nobody here has run these on your machine, and this narrows the candidates rather than certifying one.

the same builds, by member
Granite 4.0 1B
hf.co/ibm-granite/granite-4.0-1b-GGUF:Q2_KQ2_Kollama669 MiB on diskpublished by ibm-granite
hf.co/ibm-granite/granite-4.0-1b-GGUF:Q3_K_SQ3_K_Sollama749 MiB on diskpublished by ibm-granite
hf.co/ibm-granite/granite-4.0-1b-GGUF:Q3_K_LQ3_K_Lollama883 MiB on diskpublished by ibm-granite
hf.co/ibm-granite/granite-4.0-1b-GGUF:Q4_0Q4_0ollama929 MiB on diskpublished by ibm-granite
hf.co/ibm-granite/granite-4.0-1b-GGUF:Q4_K_MQ4_K_Mollama976 MiB on diskpublished by ibm-granite
hf.co/ibm-granite/granite-4.0-1b-GGUF:Q8_0Q8_0ollama1.6 GiB on diskpublished by ibm-granite
ibm-granite/granite-4.0-1bBF16vllm3.0 GiB on diskpublished by ibm-granite
hf.co/ibm-granite/granite-4.0-1b-GGUF:BF16BF16ollama3.0 GiB on diskpublished by ibm-granite
Granite 4.0 1B-BASE
hf.co/ibm-granite/granite-4.0-1b-base-GGUF:Q2_KQ2_Kollama669 MiB on diskpublished by ibm-granite
hf.co/ibm-granite/granite-4.0-1b-base-GGUF:Q3_K_SQ3_K_Sollama749 MiB on diskpublished by ibm-granite
hf.co/ibm-granite/granite-4.0-1b-base-GGUF:Q3_K_LQ3_K_Lollama883 MiB on diskpublished by ibm-granite
hf.co/ibm-granite/granite-4.0-1b-base-GGUF:Q4_0Q4_0ollama929 MiB on diskpublished by ibm-granite
hf.co/ibm-granite/granite-4.0-1b-base-GGUF:Q4_K_MQ4_K_Mollama976 MiB on diskpublished by ibm-granite
hf.co/ibm-granite/granite-4.0-1b-base-GGUF:Q8_0Q8_0ollama1.6 GiB on diskpublished by ibm-granite
ibm-granite/granite-4.0-1b-baseBF16vllm3.0 GiB on diskpublished by ibm-granite
hf.co/ibm-granite/granite-4.0-1b-base-GGUF:BF16BF16ollama3.0 GiB on diskpublished by ibm-granite
Granite-4.0-1B-BE-GGUF
hf.co/taronaeo/Granite-4.0-1B-BE-GGUF:Q2_KQ2_Kollama669 MiB on diskderived by taronaeo
hf.co/taronaeo/Granite-4.0-1B-BE-GGUF:Q3_K_SQ3_K_Sollama749 MiB on diskderived by taronaeo
hf.co/taronaeo/Granite-4.0-1B-BE-GGUF:Q3_K_LQ3_K_Lollama883 MiB on diskderived by taronaeo
hf.co/taronaeo/Granite-4.0-1B-BE-GGUF:Q4_0Q4_0ollama929 MiB on diskderived by taronaeo
hf.co/taronaeo/Granite-4.0-1B-BE-GGUF:Q4_K_MQ4_K_Mollama976 MiB on diskderived by taronaeo
hf.co/taronaeo/Granite-4.0-1B-BE-GGUF:Q8_0Q8_0ollama1.6 GiB on diskderived by taronaeo
hf.co/taronaeo/Granite-4.0-1B-BE-GGUF:BF16BF16ollama3.0 GiB on diskderived by taronaeo
hf.co/taronaeo/Granite-4.0-1B-BE-GGUF:F16F16ollama3.0 GiB on diskderived by taronaeo
granite-4.0-1b
unsloth/granite-4.0-1bBF16vllm3.0 GiB on diskderived by unsloth
Granite 4.0 350M
hf.co/unsloth/granite-4.0-350m-GGUF:IQ3_XXSIQ3_XXSollama164 MiB on diskquantized by unsloth
hf.co/unsloth/granite-4.0-350m-GGUF:IQ4_XSIQ4_XSollama211 MiB on diskquantized by unsloth
hf.co/unsloth/granite-4.0-350m-GGUF:Q4_0Q4_0ollama218 MiB on diskquantized by unsloth
hf.co/unsloth/granite-4.0-350m-GGUF:Q4_K_SQ4_K_Sollama218 MiB on diskquantized by unsloth
hf.co/unsloth/granite-4.0-350m-GGUF:Q4_K_MQ4_K_Mollama226 MiB on diskquantized by unsloth
hf.co/unsloth/granite-4.0-350m-GGUF:Q8_0Q8_0ollama360 MiB on diskquantized by unsloth
ibm-granite/granite-4.0-350mBF16vllm672 MiB on diskpublished by ibm-granite
hf.co/unsloth/granite-4.0-350m-GGUF:BF16BF16ollama675 MiB on diskquantized by unsloth
Granite 4.0 350M-BASE
ibm-granite/granite-4.0-350m-baseBF16vllm672 MiB on diskpublished by ibm-granite
Granite-4.0-350M-BE-GGUF
hf.co/taronaeo/Granite-4.0-350M-BE-GGUF:Q2_KQ2_Kollama172 MiB on diskderived by taronaeo
hf.co/taronaeo/Granite-4.0-350M-BE-GGUF:Q3_K_SQ3_K_Sollama186 MiB on diskderived by taronaeo
hf.co/taronaeo/Granite-4.0-350M-BE-GGUF:Q3_K_LQ3_K_Lollama209 MiB on diskderived by taronaeo
hf.co/taronaeo/Granite-4.0-350M-BE-GGUF:Q4_0Q4_0ollama217 MiB on diskderived by taronaeo
hf.co/taronaeo/Granite-4.0-350M-BE-GGUF:Q4_K_MQ4_K_Mollama226 MiB on diskderived by taronaeo
hf.co/taronaeo/Granite-4.0-350M-BE-GGUF:Q8_0Q8_0ollama360 MiB on diskderived by taronaeo
hf.co/taronaeo/Granite-4.0-350M-BE-GGUF:F16F16ollama675 MiB on diskderived by taronaeo
hf.co/taronaeo/Granite-4.0-350M-BE-GGUF:BF16BF16ollama675 MiB on diskderived by taronaeo
granite-4.0-350m
unsloth/granite-4.0-350mBF16vllm672 MiB on diskderived by unsloth
Granite 4.0 GUARDIAN-3B
ibm-granite/granite-guardian-4.0-3b-toxicity-jaBF16vllm6.3 GiB on diskpublished by ibm-granite
Granite 4.0 H-1B
hf.co/ibm-granite/granite-4.0-h-1b-GGUF:Q2_KQ2_Kollama561 MiB on diskpublished by ibm-granite
hf.co/ibm-granite/granite-4.0-h-1b-GGUF:Q3_K_SQ3_K_Sollama662 MiB on diskpublished by ibm-granite
hf.co/ibm-granite/granite-4.0-h-1b-GGUF:Q3_K_LQ3_K_Lollama727 MiB on diskpublished by ibm-granite
mlx-community/granite-4.0-h-1b-4bit4BITmlx785 MiB on diskquantized by mlx-community
hf.co/ibm-granite/granite-4.0-h-1b-GGUF:Q4_0Q4_0ollama828 MiB on diskpublished by ibm-granite
hf.co/ibm-granite/granite-4.0-h-1b-GGUF:Q4_K_MQ4_K_Mollama859 MiB on diskpublished by ibm-granite
mlx-community/granite-4.0-h-1b-6bit6BITmlx1.1 GiB on diskquantized by mlx-community
hf.co/ibm-granite/granite-4.0-h-1b-GGUF:Q8_0Q8_0ollama1.5 GiB on diskpublished by ibm-granite
hf.co/ibm-granite/granite-4.0-h-1b-GGUF:BF16BF16ollama2.7 GiB on diskpublished by ibm-granite
Granite 4.0 H-1B-BASE
hf.co/ibm-granite/granite-4.0-h-1b-base-GGUF:Q2_KQ2_Kollama561 MiB on diskpublished by ibm-granite
hf.co/ibm-granite/granite-4.0-h-1b-base-GGUF:Q3_K_SQ3_K_Sollama662 MiB on diskpublished by ibm-granite
hf.co/ibm-granite/granite-4.0-h-1b-base-GGUF:Q3_K_LQ3_K_Lollama727 MiB on diskpublished by ibm-granite
hf.co/ibm-granite/granite-4.0-h-1b-base-GGUF:Q4_0Q4_0ollama828 MiB on diskpublished by ibm-granite
hf.co/ibm-granite/granite-4.0-h-1b-base-GGUF:Q4_K_MQ4_K_Mollama859 MiB on diskpublished by ibm-granite
hf.co/ibm-granite/granite-4.0-h-1b-base-GGUF:Q8_0Q8_0ollama1.5 GiB on diskpublished by ibm-granite
hf.co/ibm-granite/granite-4.0-h-1b-base-GGUF:BF16BF16ollama2.7 GiB on diskpublished by ibm-granite
Granite 4.0 H-350M
hf.co/ibm-granite/granite-4.0-h-350m-GGUF:Q2_KQ2_Kollama152 MiB on diskpublished by ibm-granite
hf.co/ibm-granite/granite-4.0-h-350m-GGUF:Q3_K_SQ3_K_Sollama172 MiB on diskpublished by ibm-granite
hf.co/ibm-granite/granite-4.0-h-350m-GGUF:Q3_K_LQ3_K_Lollama185 MiB on diskpublished by ibm-granite
hf.co/ibm-granite/granite-4.0-h-350m-GGUF:Q4_0Q4_0ollama206 MiB on diskpublished by ibm-granite
hf.co/ibm-granite/granite-4.0-h-350m-GGUF:Q4_K_SQ4_K_Sollama206 MiB on diskpublished by ibm-granite
hf.co/ibm-granite/granite-4.0-h-350m-GGUF:Q4_K_MQ4_K_Mollama212 MiB on diskpublished by ibm-granite
mlx-community/granite-4.0-h-350m-8bit8BITmlx345 MiB on diskquantized by mlx-community
hf.co/ibm-granite/granite-4.0-h-350m-GGUF:Q8_0Q8_0ollama349 MiB on diskpublished by ibm-granite
hf.co/ibm-granite/granite-4.0-h-350m-GGUF:BF16BF16ollama653 MiB on diskpublished by ibm-granite
Granite 4.0 H-350M-BASE
ibm-granite/granite-4.0-h-350m-baseBF16vllm649 MiB on diskpublished by ibm-granite
Granite-4.0-H-350M-BE-GGUF
hf.co/taronaeo/Granite-4.0-H-350M-BE-GGUF:Q2_KQ2_Kollama152 MiB on diskderived by taronaeo
hf.co/taronaeo/Granite-4.0-H-350M-BE-GGUF:Q3_K_SQ3_K_Sollama172 MiB on diskderived by taronaeo
hf.co/taronaeo/Granite-4.0-H-350M-BE-GGUF:Q3_K_LQ3_K_Lollama185 MiB on diskderived by taronaeo
hf.co/taronaeo/Granite-4.0-H-350M-BE-GGUF:Q4_0Q4_0ollama206 MiB on diskderived by taronaeo
hf.co/taronaeo/Granite-4.0-H-350M-BE-GGUF:Q4_K_SQ4_K_Sollama206 MiB on diskderived by taronaeo
hf.co/taronaeo/Granite-4.0-H-350M-BE-GGUF:Q4_K_MQ4_K_Mollama212 MiB on diskderived by taronaeo
hf.co/taronaeo/Granite-4.0-H-350M-BE-GGUF:Q8_0Q8_0ollama349 MiB on diskderived by taronaeo
hf.co/taronaeo/Granite-4.0-H-350M-BE-GGUF:BF16BF16ollama653 MiB on diskderived by taronaeo
hf.co/taronaeo/Granite-4.0-H-350M-BE-GGUF:F16F16ollama653 MiB on diskderived by taronaeo
Granite 4.0 H-MICRO
hf.co/unsloth/granite-4.0-h-micro-GGUF:IQ1_SIQ1_Sollama735 MiB on diskquantized by unsloth
hf.co/unsloth/granite-4.0-h-micro-GGUF:IQ2_XXSIQ2_XXSollama898 MiB on diskquantized by unsloth
hf.co/unsloth/granite-4.0-h-micro-GGUF:IQ3_XXSIQ3_XXSollama1.2 GiB on diskquantized by unsloth
mlx-community/granite-4.0-h-micro-4bit4BITmlx1.7 GiB on diskquantized by mlx-community
hf.co/unsloth/granite-4.0-h-micro-GGUF:Q4_0Q4_0ollama1.7 GiB on diskquantized by unsloth
hf.co/unsloth/granite-4.0-h-micro-GGUF:Q4_K_MQ4_K_Mollama1.8 GiB on diskquantized by unsloth
hf.co/unsloth/granite-4.0-h-micro-GGUF:Q8_0Q8_0ollama3.2 GiB on diskquantized by unsloth
hf.co/unsloth/granite-4.0-h-micro-GGUF:BF16BF16ollama5.9 GiB on diskquantized by unsloth
granite-4.0-h-tiny-4bit
mlx-community/granite-4.0-h-tiny-4bit4BITmlx3.6 GiB on diskderived by mlx-community
Granite 4.0 H-SMALL
lmstudio-community/granite-4.0-h-small-MLX-4bit4BITmlx16.9 GiB on diskquantized by lmstudio-community
lmstudio-community/granite-4.0-h-small-MLX-6bit6BITmlx24.4 GiB on diskquantized by lmstudio-community
lmstudio-community/granite-4.0-h-small-MLX-8bit8BITmlx31.9 GiB on diskquantized by lmstudio-community
Granite 4.0 H-TINY
lmstudio-community/granite-4.0-h-tiny-MLX-4bit4BITmlx3.6 GiB on diskquantized by lmstudio-community
lmstudio-community/granite-4.0-h-tiny-MLX-6bit6BITmlx5.3 GiB on diskquantized by lmstudio-community
RedHatAI/granite-4.0-h-tiny-FP8-dynamicFP8vllm6.6 GiB on diskquantized by RedHatAI
lmstudio-community/granite-4.0-h-tiny-MLX-8bit8BITmlx6.9 GiB on diskquantized by lmstudio-community
Granite-4.0-H-Tiny-4bit-DWQ
mlx-community/Granite-4.0-H-Tiny-4bit-DWQ4BITmlx3.6 GiB on diskderived by mlx-community
granite-4.0-micro-unsloth-bnb-4bit
unsloth/granite-4.0-micro-unsloth-bnb-4bitBITSANDBYTESvllm2.4 GiB on diskderived by unsloth
Granite 4.0 SPEECH-1B
hf.co/ibm-granite/granite-4.0-1b-speech-GGUF:Q4_K_MQ4_K_Mollama1.1 GiB on diskpublished by ibm-granite
hf.co/ibm-granite/granite-4.0-1b-speech-GGUF:Q5_K_MQ5_K_Mollama1.2 GiB on diskpublished by ibm-granite
hf.co/ibm-granite/granite-4.0-1b-speech-GGUF:Q8_0Q8_0ollama1.8 GiB on diskpublished by ibm-granite
hf.co/ibm-granite/granite-4.0-1b-speech-GGUF:BF16BF16ollama3.4 GiB on diskpublished by ibm-granite
ibm-granite/granite-4.0-1b-speechBF16vllm4.3 GiB on diskpublished by ibm-granite
Granite 4.0 VISION-3B
ibm-granite/granite-4.0-3b-visionBF16vllm8.8 GiB on diskpublished by ibm-granite
ask your own gram

Your concierge can answer this from the network rather than from this page. The ask carries the operator id, so it resolves to a capability and an engine — not to a name somebody has to recognise.

What has this network measured about the Granite 4.0 family (epn.family.granite-4-0), and can my gram run any of it? See /inferences/granite-4-0

open a gramx with this ask →epn.family.granite-4-0