What are the hardware requirements for Qwen1.5 32B Chat 4bit?

Qwen1.5 32B Chat 4bit requires approximately 54.9 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen1.5 32B Chat 4bit and how large is it?

Qwen1.5 32B Chat 4bit is developed by mlx-community, a model with 32b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Qwen1.5 32B Chat 4bit perform on standard benchmarks?

Qwen1.5 32B Chat 4bit has the following published scores: MMLU 74.99, LMSYS ELO 1203. Compare against reference models on this page or on the LLM Explorer leaderboards.

Qwen1.5 32B Chat 4bit by mlx-community — VRAM 54.9GB, 32K context

Name: Qwen1.5 32B Chat 4bit
Author: mlx-community

Qwen1.5 32B Chat 4bit is an open-source language model by mlx-community. Features: 32b LLM, VRAM: 54.9GB, Context: 32K, License: other, Quantized, LLM Explorer Score: 0.25, ELO: 1203, Arc: 66, HellaSwag: 85.5, MMLU: 75, GSM8K: 7.1.

4bit Chat Conversational En Mlx Quantized Qwen2 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/mlx-community/Qwen1.5-32B-Chat-4bit

Qwen1.5 32B Chat 4bit Benchmarks

LMSys ELO 1203 vs 1272 (so35) -5.4%

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

Qwen1.5 32B Chat 4bit Parameters and Internals

Model Type

text-generation

Additional Notes

This model was converted to MLX format.

LLM Name	Qwen1.5 32B Chat 4bit
Repository 🤗	https://huggingface.co/mlx-community/Qwen1.5-32B-Chat-4bit
Base Model(s)	Qwen/Qwen1.5-32B-Chat Qwen/Qwen1.5-32B-Chat
Model Size	32b
Required VRAM	54.9 GB
Updated	2026-07-22
Maintainer	mlx-community
Model Type	qwen2
Model Files	5.4 GB: 1-of-4 5.4 GB: 1-of-7 5.4 GB: 2-of-4 5.3 GB: 2-of-7 5.4 GB: 3-of-4 5.4 GB: 3-of-7 3.3 GB: 4-of-4 5.3 GB: 4-of-7 5.3 GB: 5-of-7 5.4 GB: 6-of-7 3.3 GB: 7-of-7
Supported Languages	en
Quantization Type	4bit
Model Architecture	Qwen2ForCausalLM
License	other
Context Length	32768
Model Max Length	32768
Transformers Version	4.38.0
Padding Token	<\|endoftext\|>
Vocabulary Size	152064
Torch Data Type	bfloat16
Errors	replace

Rank the Qwen1.5 32B Chat 4bit capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Qwen1.5 32B Chat 4bit

Best Alternatives	Context / RAM	Downloads	Likes
...Logic Mix 3 32B Mlx OptiQ 5bit	128K / 22.3 GB	41	1
...pSeek R1 Distill Qwen 32B 4bit	128K / 18.5 GB	7795	51
Hydraulic Deepseek 16bit	128K / 65.8 GB	52	0
...k R1 Distill Qwen 32B Bnb 4bit	128K / 19.2 GB	2717	29
...till Qwen 32B Abliterated 4bit	128K / 18.5 GB	888	7
QwQ 32B Unsloth Bnb 4bit	128K / 22.5 GB	179	47
...ogito V1 Preview Qwen 32B 4bit	128K / 18.5 GB	43	5
...T1 Flash Lightest 32B Mlx 4Bit	128K / 18.5 GB	231	8
QwQ 32B 4bit	128K / 18.5 GB	132	38
QwQ 32B Bnb 4bit	128K / 19.2 GB	157	4