Model Intelligence Sheet
1bit-MONSTER/Qwen2.5-7B-Instruct-GGUF overview
Qwen2.5 7B Instruct — GGUF Q4 K M Qwen's own Q4 K M GGUF 2 shards , re hosted with measured performance for the 1bit engine https://github.com/1bit MONSTER/eng…
Runs locally from ~657.9 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
Model Details
| Model ID | 1bit-MONSTER/Qwen2.5-7B-Instruct-GGUF |
|---|---|
| Author | 1bit-MONSTER |
| Pipeline | — |
| License | apache-2.0 |
| Base model | Qwen/Qwen2.5-7B-Instruct |
| Last modified | 2026-09-26T13:55:24.000Z |
Model README
---
license: apache-2.0
base_model:
- Qwen/Qwen2.5-7B-Instruct
tags:
- gguf
---
Qwen2.5-7B-Instruct — GGUF (Q4_K_M)
Qwen's own Q4_K_M GGUF (2 shards), re-hosted with measured performance for the
1bit engine on Strix Halo.
Contents
qwen2.5-7b-instruct-q4_k_m-00001-of-00002.ggufqwen2.5-7b-instruct-q4_k_m-00002-of-00002.gguf
Measured performance (Strix Halo, Vulkan)
pp512: 1306 tok/s · tg128: 40.3 tok/s
Running it
Point at the first shard — llama.cpp finds the rest automatically:
1bit serve -m qwen2.5-7b-instruct-q4_k_m-00001-of-00002.gguf --device vulkanAttribution
- Model and quantization: Qwen/Qwen2.5-7B-Instruct-GGUF, Apache 2.0.
- License: Apache 2.0, inherited from the base model.
Run 1bit-MONSTER/Qwen2.5-7B-Instruct-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models