granite-4.1-3b-fp8

ibm-granite/granite-4.1-3b-fp8

Text Generation3.7B parameterstransformersLicense: apache-2.0
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
Downloads 30D
2,950
Total downloads
12K
Gained 7D
Gained 30D
Likes
8
Rank · tracked models
#14,131
this week
Parameters
3.7B
Last source update
Apr 21, 2026

Downloads over time

Cumulative total downloads observed by OpenModelStats

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-08-24. Charts appear as daily observations accumulate.

Likes over time

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-08-24. Charts appear as daily observations accumulate.

Rank among tracked models

Lower is better

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-08-24. Charts appear as daily observations accumulate.

Overview

granite-4.1-3b-fp8 is a text generation model published by ibm-granite. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it 16h ago.

Published
Apr 20, 2026
Last updated
Apr 21, 2026
Library
transformers
License
apache-2.0
Task
Text Generation
Parameters
3,660,741,120
Spaces
Derivative models
Velocity 7D/day
transformerssafetensorsgranitetext-generationlanguagegranite-4.1ggufconversationalbase_model:ibm-granite/granite-4.1-3bbase_model:quantized:ibm-granite/granite-4.1-3blicense:apache-2.0endpoints_compatible

Publisher

ibm-graniteView publisher statistics →

Derived from ibm-granite/granite-4.1-3b (reported by the source; parent not yet tracked).

Similar models

Models similar to granite-4.1-3b-fp8
ModelDL 30D
japanese-large-lm-3.6bline-corporation72
Devstral-Small-2505-MLX-4bitlmstudio-community9,794
Magistral-Small-2506-MLX-4bitlmstudio-community7,520
Qwen3.6-35B-A3B-RotorQuant-MLX-2bitmajentik1,603
Llama-3.2-3B-Instruct-FP8-dynamicRedHatAI1,552
Llama-3.2-3B-Instruct-quantized.w8a8RedHatAI1,462