1bit-MONSTER/Qwen1.5-MoE-A2.7B-Chat-GGUF overview
Qwen1.5 MoE A2.7B Chat — GGUF Q4 K M Community Q4 K M GGUF for Qwen's original small MoE 14.3B total, ~2.7B active , re hosted with measured performance for th…
Runs locally from ~8.84 GB disk (12 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Qwen1.5-MoE-A2.7B-Chat.Q4_K_M.gguf | GGUF | GGUF | 8.84 GB | Download |
Model Details
| Model ID | 1bit-MONSTER/Qwen1.5-MoE-A2.7B-Chat-GGUF |
|---|---|
| Author | 1bit-MONSTER |
| Pipeline | — |
| License | other |
| Base model | Qwen/Qwen1.5-MoE-A2.7B-Chat |
| Last modified | 2026-09-26T14:28:00.000Z |
Model README
---
license: other
license_name: tongyi-qianwen
license_link: LICENSE
base_model:
- Qwen/Qwen1.5-MoE-A2.7B-Chat
tags:
- gguf
- moe
---
Qwen1.5-MoE-A2.7B-Chat — GGUF (Q4_K_M)
Community Q4_K_M GGUF for Qwen's original small MoE (14.3B total, ~2.7B active),
re-hosted with measured performance for the
1bit engine on Strix Halo.
Licensed under Qwen's original Tongyi Qianwen license — commercial use is
allowed, with a separate license required only if your product/service exceeds 100M
monthly active users.
Contents
Qwen1.5-MoE-A2.7B-Chat.Q4_K_M.gguf
Measured performance (Strix Halo, Vulkan)
pp512: 1896 tok/s · tg128: 89.7 tok/s
Running it
1bit serve -m Qwen1.5-MoE-A2.7B-Chat.Q4_K_M.gguf --device vulkanAttribution
- Base model: Qwen/Qwen1.5-MoE-A2.7B-Chat.
- Quantization: RichardErkhov/Qwen_-_Qwen1.5-MoE-A2.7B-Chat-gguf.
- Tongyi Qianwen is licensed under the Tongyi Qianwen LICENSE AGREEMENT, Copyright (c) Alibaba Cloud. All Rights Reserved.
Run 1bit-MONSTER/Qwen1.5-MoE-A2.7B-Chat-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models