Qwen2.5 Coder 3B Instruct 4bit is an open-source language model by mlx-community. Features: 3b LLM, VRAM: 1.7GB, Context: 32K, License: other, Quantized, Instruction-Based, Code Generating, LLM Explorer Score: 0.18.
4-bit 4bit Base model:quantized:qwen/qwen... Base model:qwen/qwen2.5-coder-... Chat Code Codegen Codeqwen Conversational Deploy:azure En Endpoints compatible Instruct Mlx Quantized Qwen Qwen-coder Qwen2 Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/mlx-community/Qwen2.5-Coder-3B-Instruct-4bit
Qwen2.5 Coder 3B Instruct 4bit Benchmarks
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)
Qwen2.5 Coder 3B Instruct 4bit Parameters and Internals
| LLM Name | Qwen2.5 Coder 3B Instruct 4bit |
| Repository 🤗 | https://huggingface.co/mlx-community/Qwen2.5-Coder-3B-Instruct-4bit |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 1.7 GB |
| Updated | 2026-05-08 |
| Maintainer | mlx-community |
| Model Type | qwen2 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Generates Code | Yes |
| Model Architecture | Qwen2ForCausalLM |
| License | other |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.43.1 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Qwen2.5 Coder 3B Instruct 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...2.5 Coder 3B Instruct Bnb 4bit | 32K / 2 GB | 21356 | 7 |
| Qwen3b Lora Finetune | 32K / 6.2 GB | 0 | 1 |
| Qwen3b Lora Finetune | 32K / 6.2 GB | 0 | 1 |
| Tessa T1 3B | 117K / 6.2 GB | 16 | 5 |
| UIGEN T1.5 3B | 117K / 6.2 GB | 10 | 1 |
| Coder GRPO 3B | 32K / 6.2 GB | 2671 | 7 |
| Qwen2.5 Coder 3B Instruct | 32K / 6.2 GB | 451109 | 101 |
| Qwen 2.5 3b Smarteaz 0.01a | 32K / 6.3 GB | 26 | 1 |
| Q2.5 CodeR1 3B | 32K / 6.2 GB | 0 | 1 |
| VisCoder2 3B | 32K / 6.2 GB | 16 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Qwen2.5-Coder-3B-Instruct-4bit .
Rank the Qwen2.5 Coder 3B Instruct 4bit 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! 🌟
What open-source LLMs or SLMs are you in search of? 53570 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a