Qwen2.5 3B Instruct GPTQ Int4 is an open-source language model by Qwen. Features: 3b LLM, VRAM: 2.1GB, Context: 32K, License: other, Quantized, Instruction-Based, LLM Explorer Score: 0.18.
Arxiv:2407.10671 4-bit Base model:quantized:qwen/qwen... Base model:qwen/qwen2.5-3b-ins... Chat Conversational En Endpoints compatible Gptq Instruct Quantized Qwen2 Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen2.5-3B-Instruct-GPTQ-Int4
Qwen2.5 3B Instruct GPTQ Int4 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 3B Instruct GPTQ Int4 Parameters and Internals
| LLM Name | Qwen2.5 3B Instruct GPTQ Int4 |
| Repository 🤗 | https://huggingface.co/Qwen/Qwen2.5-3B-Instruct-GPTQ-Int4 |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 2.1 GB |
| Updated | 2026-07-10 |
| Maintainer | Qwen |
| Model Type | qwen2 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Model Architecture | Qwen2ForCausalLM |
| License | other |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.39.3 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | float16 |
| Errors | replace |
Best Alternatives to Qwen2.5 3B Instruct GPTQ Int4
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen2.5 3B Instruct GPTQ Int8 | 32K / 3.5 GB | 274 | 3 |
| VibeThinker 3B 8bit | 128K / 3.3 GB | 2691 | 3 |
| Qwen2.5 3B Legal Id Sft | 32K / 6.2 GB | 730 | 0 |
| ...sa Assyifa Putri Legal Chatbot | 32K / 6.2 GB | 208 | 0 |
| Legalbot Exp1 | 32K / 6.2 GB | 187 | 0 |
| ...wen2.5 Coder 3B Instruct V13.1 | 32K / 6.2 GB | 81 | 0 |
| Qwen2.5 3B Indonesian Legal | 32K / 6.2 GB | 67 | 0 |
| Qwen2.5 3B Alpaca Id | 32K / 6.2 GB | 60 | 0 |
| ...egal Chatbot Qwen3b Sft Merged | 32K / 6.2 GB | 72 | 0 |
| Qwen Indo SFT | 32K / 6.2 GB | 23 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen2.5-3B-Instruct-GPTQ-Int4 .
Rank the Qwen2.5 3B Instruct GPTQ Int4 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? 54990 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