Model Intelligence Sheet
1bit-MONSTER/Qwen3-14B-GGUF overview
Qwen3 14B — GGUF Q4 K M Qwen's own Q4 K M GGUF for Qwen3 14B, re hosted with measured performance for the 1bit engine https://github.com/1bit MONSTER/engine on…
Runs locally from ~8.38 GB disk (12 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 |
|---|---|---|---|---|
| Qwen3-14B-Q4_K_M.gguf | GGUF | Q4_K_M | 8.38 GB | Download |
Model Details
| Model ID | 1bit-MONSTER/Qwen3-14B-GGUF |
|---|---|
| Author | 1bit-MONSTER |
| Pipeline | — |
| License | apache-2.0 |
| Base model | Qwen/Qwen3-14B |
| Last modified | 2026-09-26T13:33:22.000Z |
Model README
---
license: apache-2.0
base_model:
- Qwen/Qwen3-14B
tags:
- gguf
---
Qwen3-14B — GGUF (Q4_K_M)
Qwen's own Q4_K_M GGUF for Qwen3-14B, re-hosted with measured performance for the
1bit engine on Strix Halo.
Contents
Qwen3-14B-Q4_K_M.gguf
Measured performance (Strix Halo, Vulkan)
pp512: 594 tok/s · tg128: 23.0 tok/s
Running it
1bit serve -m Qwen3-14B-Q4_K_M.gguf --device vulkanAttribution
- Model and quantization: Qwen/Qwen3-14B-GGUF, Apache 2.0.
- License: Apache 2.0, inherited from the base model.
Run 1bit-MONSTER/Qwen3-14B-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models