36 lines
1.0 KiB
Markdown
36 lines
1.0 KiB
Markdown
---
|
|
license: apache-2.0
|
|
inference: false
|
|
base_model: Qwen/Qwen3-4B-Instruct
|
|
base_model_relation: quantized
|
|
tags: [green, llmware-chat, p4, gguf,emerald]
|
|
---
|
|
|
|
# qwen3-4b-instruct-gguf
|
|
|
|
**qwen3-4b-instruct-gguf** is a GGUF Q4_K_M int4 quantized version of [Qwen3-4B-Instruct](https://www.huggingface.co/Qwen/Qwen3-4B-Instruct), providing a very fast inference implementation, optimized for AI PCs.
|
|
|
|
This is from the latest release series from Qwen, and has 'thinking' capability expressed as 'think' tokens.
|
|
|
|
This model will run on an AI PC, with GPU acceleration and 32 GB of memory.
|
|
|
|
### Model Description
|
|
|
|
- **Developed by:** Qwen
|
|
- **Model type:** qwen3
|
|
- **Parameters:** 4 billion
|
|
- **Model Parent:** Qwen/Qwen3-4B-Instruct
|
|
- **Language(s) (NLP):** English
|
|
- **License:** Apache 2.0
|
|
- **Uses:** Chat, general-purpose LLM
|
|
- **Quantization:** int4
|
|
|
|
|
|
## Model Card Contact
|
|
|
|
[llmware on github](https://www.github.com/llmware-ai/llmware)
|
|
|
|
[llmware on hf](https://www.huggingface.co/llmware)
|
|
|
|
[llmware website](https://www.llmware.ai)
|