LLMs · Alibaba

Qwen1.5 MoE A2.7B Chat

Name: Qwen1.5 MoE A2.7B Chat
Author: Alibaba

Parameters: 14B (2.7B active)
Architecture: Mixture of experts
Max context: 8K tokens
License: tongyi-qianwen
Released: 2024-03

How to run it

Original weights · Hugging Face

Full-precision files from Alibaba, for fine-tuning, vLLM, Transformers.

huggingface.co/Qwen/Qwen1.5-MoE-A2.7B-Chat (opens in a new tab)

No sign-in needed.

Links checked 2 days ago against Hugging Face, Ollama and GitHub.

Apps that run Qwen1.5 MoE A2.7B Chat

Our pick for each kind of computer, assuming the model fits in its memory. Pick your own GPU or device in the Model Finder for an exact answer.

Mac (Apple silicon)

LM Studio

Runs the MLX build, typically 35–90% faster than GGUF for a model with 2.7B active parameters on Apple silicon.

Also good:

Windows PC, NVIDIA GPU

Docker Model Runner

Handy if you already work in Docker.

Also good:

Windows PC, AMD Radeon

Docker Model Runner

Handy if you already work in Docker.

Also good:

Text Generation WebUI

Linux, NVIDIA GPU

Docker Model Runner

Handy if you already work in Docker.

Also good:

Linux server, 80 GB+ GPUs

vLLM

The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.

Also good:

App	Type	Opens it as	Systems	Engine	Start
LM Studio	Desktop app	MLX	macOSWindowsLinux	llama.cpp, MLX	Open in LM Studio
Jan	Desktop app	MLX	macOSWindowsLinux	llama.cpp, MLX	Get Jan
MLX LM	CLI + API	MLX	macOS	MLX	`mlx_lm.chat --model mlx-community/Qwen1.5-MoE-A2.7B-Chat-4bit`
vLLM	Server	Original weights	WSLWindowsLinux	vLLM	`vllm serve Qwen/Qwen1.5-MoE-A2.7B-Chat`
SGLang	Server	Original weights	WSLWindowsLinux	SGLang	`python3 -m sglang.launch_server --model-path Qwen/Qwen1.5-MoE-A2.7B-Chat`
Docker Model Runner	CLI + API	Original weights	macOSWindowsLinux	llama.cpp, vLLM	`docker model run hf.co/Qwen/Qwen1.5-MoE-A2.7B-Chat`
Unsloth Desktop	Desktop app	MLX	macOSWindowsLinux	llama.cpp, MLX, stable-diffusion.cpp	Get Unsloth Desktop
Atomic Chat	Desktop app	MLX	macOSWindowsLinux	llama.cpp, MLX-VLM	Open in Atomic Chat
Text Generation WebUI	Desktop app	Original weights	macOSWindowsLinux	llama.cpp, Transformers, ExLlamaV3	Get Text Generation WebUI
Msty Studio	Desktop app	MLX	macOSWindowsLinux	Ollama, llama.cpp, MLX	Get Msty Studio
Inferencer	Desktop app	MLX	macOS	MLX	Get Inferencer
exo	Server	MLX	macOSLinux	MLX	Get exo

Which apps can open a model depends on the files published for it: GGUF for llama.cpp-based apps, MLX for Apple’s engine, the original weights for vLLM and SGLang. Compare every app.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps. Try another context length.

Quantization	Quality	Weights	Total at 8K context	Download
`Q2_K`	Low	5.7 GB	7.9 GB	All files (opens in a new tab)
`Q3_K_M`	Low	7.0 GB	9.2 GB	All files (opens in a new tab)
`Q4_K_M`	Good	8.7 GB	10.9 GB	All files (opens in a new tab)
`Q5_K_M`	High	10.2 GB	12.4 GB	All files (opens in a new tab)
`Q6_K`	High	11.7 GB	14.0 GB	All files (opens in a new tab)
`Q8_0`	Very high	15.2 GB	17.4 GB	All files (opens in a new tab)
`F16`	Full	28.6 GB	30.9 GB	Original weights (opens in a new tab)

Best hardware for Qwen1.5 MoE A2.7B Chat

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc B570 (launch price $219) at Q3_K_M.

Quality	Hardware	Quant	Memory	Speed	Runs
24Basic quality (D) · 24 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.	AMD Radeon RX 7900 XTX	`Q8_0`	18.6 GB / 24.0 GB	111 tok/s	Runs great
24Basic quality (D) · 24 of 100: how capable the model is at F16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.	Apple M4 Max (64 GB)	`F16`	34.7 GB / 48.0 GB	41.1 tok/s	Runs great
24Basic quality (D) · 24 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 3090	`Q8_0`	18.6 GB / 24.0 GB	119 tok/s	Runs great
24Basic quality (D) · 24 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 4090	`Q8_0`	18.6 GB / 24.0 GB	124 tok/s	Runs great
23Basic quality (D) · 23 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.	AMD Radeon RX 9070 XT	`Q5_K_M`	13.2 GB / 16.0 GB	120 tok/s	Runs great
23Basic quality (D) · 23 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.	Apple M4 Pro (24 GB)	`Q5_K_M`	13.7 GB / 16.1 GB	67.5 tok/s	Runs great
23Basic quality (D) · 23 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 4060 Ti 16GB	`Q5_K_M`	13.2 GB / 16.0 GB	78.5 tok/s	Runs great
23Basic quality (D) · 23 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 4070 Ti SUPER	`Q5_K_M`	13.2 GB / 16.0 GB	134 tok/s	Runs great
23Basic quality (D) · 23 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 4080 SUPER	`Q5_K_M`	13.2 GB / 16.0 GB	140 tok/s	Runs great
23Basic quality (D) · 23 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 5060 Ti 16GB	`Q5_K_M`	13.2 GB / 16.0 GB	106 tok/s	Runs great

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.