Model Intelligence Sheet
1bit-MONSTER/granite-4.1-3b-GGUF overview
granite 4.1 3b — GGUF Q4 K M IBM's own Q4 K M GGUF, re hosted with measured performance for the 1bit engine https://github.com/1bit MONSTER/engine on Strix Hal…
Runs locally from ~1.96 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
1 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| granite-4.1-3b-Q4_K_M.gguf | GGUF | Q4_K_M | 1.96 GB | Download |
Model Details
| Model ID | 1bit-MONSTER/granite-4.1-3b-GGUF |
|---|---|
| Author | 1bit-MONSTER |
| Pipeline | — |
| License | apache-2.0 |
| Base model | ibm-granite/granite-4.1-3b |
| Last modified | 2026-09-26T15:27:07.000Z |
Model README
---
license: apache-2.0
base_model:
- ibm-granite/granite-4.1-3b
tags:
- gguf
---
granite-4.1-3b — GGUF (Q4_K_M)
IBM's own Q4_K_M GGUF, re-hosted with measured performance for the
1bit engine on Strix Halo.
Contents
granite-4.1-3b-Q4_K_M.gguf
Measured performance (Strix Halo, Vulkan)
pp512: 2688 tok/s · tg128: 74.5 tok/s
Running it
1bit serve -m granite-4.1-3b-Q4_K_M.gguf --device vulkanAttribution
- Model and quantization: ibm-granite/granite-4.1-3b-GGUF, Apache 2.0.
- License: Apache 2.0, inherited from the base model.
Run 1bit-MONSTER/granite-4.1-3b-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models