LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Qwen2.5 Coder 32B Instruct 3bit by mlx-community

 »  All LLMs  »  mlx-community  »  Qwen2.5 Coder 32B Instruct 3bit   URL Share it on

  83   

Qwen2.5 Coder 32B Instruct 3bit is an open-source language model by mlx-community. Features: 32b LLM, VRAM: 14.3GB, Context: 32K, License: apache-2.0, Quantized, Instruction-Based, Code Generating, LLM Explorer Score: 0.29, ELO: 1220, HumanEval: 83.2.

  3-bit   3bit Base model:quantized:qwen/qwen... Base model:qwen/qwen2.5-coder-...   Chat   Code   Codegen   Codeqwen   Conversational   En   Endpoints compatible   Instruct   Mlx   Quantized   Qwen   Qwen-coder   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Qwen2.5-Coder-32B-Instruct-3bit 

Qwen2.5 Coder 32B Instruct 3bit Benchmarks

LMSys ELO: 1220 vs 1272 (so35)-4.1%
HumanEvalA: 63.38
Python Eva: 83.2 vs 92 (so35)-9.6%
Java Eval: 73.69
Javascript: 76.05
CPP Eval: 81.95
PHP Eval: 73.59
Julia Eval: 58.15
D Eval: 26.98
Lua Eval: 46.04
R Eval: 52.73
Racket Eva: 61.54
Rust Eval: 68.53
Swift Eval: 58.12
LLME Score: 0.28858
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen2.5 Coder 32B Instruct 3bit (mlx-community/Qwen2.5-Coder-32B-Instruct-3bit)
🌟 Advertise your project 🚀

Qwen2.5 Coder 32B Instruct 3bit Parameters and Internals

Model Type 
text generation
Additional Notes 
The model was converted into MLX format using mlx-lm version 0.19.3.
Supported Languages 
en (high)
Input Output 
Input Format:
chat-based prompt
Accepted Modalities:
text
LLM NameQwen2.5 Coder 32B Instruct 3bit
Repository 🤗https://huggingface.co/mlx-community/Qwen2.5-Coder-32B-Instruct-3bit 
Base Model(s)  Qwen/Qwen2.5-Coder-32B-Instruct   Qwen/Qwen2.5-Coder-32B-Instruct
Model Size32b
Required VRAM14.3 GB
Updated2026-03-14
Maintainermlx-community
Model Typeqwen2
Instruction-BasedYes
Model Files  5.3 GB: 1-of-3   5.3 GB: 2-of-3   3.7 GB: 3-of-3
Supported Languagesen
Quantization Type3bit
Generates CodeYes
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.43.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen2.5 Coder 32B Instruct 3bit

Best Alternatives
Context / RAM
Downloads
Likes
....5 Coder 32B Instruct Bnb 4bit32K / 19.2 GB55196
...wen2.5 Coder 32B Instruct 4bit32K / 18.5 GB163512
...wen2.5 Coder 32B Instruct 8bit32K / 34.9 GB119013
...truct Gptqmodel 4bit Vortex V132K / 21.3 GB5816
...y Qwen2.5coder 32B V24.1q 200K195K / 65.8 GB82
Qwen2.5 32B YOYO MIX128K / 65.7 GB72
Qwen2.5 Coder 32B YOYO128K / 65.8 GB82
QwQ Qwen2.5 Coder Instruct 32B128K / 65.8 GB430
QwQenSeek Coder128K / 65.7 GB345
Rombos Coder V2.5 Qwen 32B128K / 65.8 GB2419
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Qwen2.5-Coder-32B-Instruct-3bit.

Rank the Qwen2.5 Coder 32B Instruct 3bit Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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  

What open-source LLMs or SLMs are you in search of? 53232 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer