58 lines
3.7 KiB
Markdown
58 lines
3.7 KiB
Markdown
---
|
|
license: apache-2.0
|
|
language:
|
|
- en
|
|
base_model:
|
|
- Qwen/Qwen3-8B
|
|
pipeline_tag: text-generation
|
|
library_name: transformers
|
|
tags:
|
|
- text-generation-inference
|
|
- moe
|
|
---
|
|
|
|
# **Qwen3-8B-GGUF**
|
|
|
|
> Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support
|
|
|
|
## Model Files
|
|
|
|
| File Name | Size | Quantization | Format | Description |
|
|
| ---------------------- | ------- | ------------ | ------ | -------------------------------- |
|
|
| `Qwen3_8B.F32.gguf` | 32.8 GB | FP32 | GGUF | Full precision (float32) version |
|
|
| `Qwen3_8B.BF16.gguf` | 16.4 GB | BF16 | GGUF | BFloat16 precision version |
|
|
| `Qwen3_8B.F16.gguf` | 16.4 GB | FP16 | GGUF | Float16 precision version |
|
|
| `Qwen3_8B.Q2_K.gguf` | 3.28 GB | Q2\_K | GGUF | 2-bit quantized (K variant) |
|
|
| `Qwen3_8B.Q3_K_M.gguf` | 4.12 GB | Q3\_K\_M | GGUF | 3-bit quantized (K M variant) |
|
|
| `Qwen3_8B.Q3_K_S.gguf` | 3.77 GB | Q3\_K\_S | GGUF | 3-bit quantized (K S variant) |
|
|
| `Qwen3_8B.Q4_K_M.gguf` | 5.03 GB | Q4\_K\_M | GGUF | 4-bit quantized (K M variant) |
|
|
| `Qwen3_8B.Q4_K_S.gguf` | 4.8 GB | Q4\_K\_S | GGUF | 4-bit quantized (K S variant) |
|
|
| `Qwen3_8B.Q5_K_M.gguf` | 5.85 GB | Q5\_K\_M | GGUF | 5-bit quantized (K M variant) |
|
|
| `Qwen3_8B.Q8_0.gguf` | 8.71 GB | Q8\_0 | GGUF | 8-bit quantized |
|
|
| `.gitattributes` | 2.08 kB | — | — | Git LFS tracking file |
|
|
| `config.json` | 31 B | — | — | Configuration placeholder |
|
|
| `README.md` | 31 B | — | — | Model documentation |
|
|
|
|
## Quants Usage
|
|
|
|
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
|
|
|
|
| Link | Type | Size/GB | Notes |
|
|
|:-----|:-----|--------:|:------|
|
|
| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q2_K.gguf) | Q2_K | 0.4 | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q3_K_S.gguf) | Q3_K_S | 0.5 | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality |
|
|
| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q3_K_L.gguf) | Q3_K_L | 0.5 | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.IQ4_XS.gguf) | IQ4_XS | 0.6 | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q4_K_S.gguf) | Q4_K_S | 0.6 | fast, recommended |
|
|
| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q4_K_M.gguf) | Q4_K_M | 0.6 | fast, recommended |
|
|
| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q5_K_S.gguf) | Q5_K_S | 0.6 | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q5_K_M.gguf) | Q5_K_M | 0.7 | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q6_K.gguf) | Q6_K | 0.7 | very good quality |
|
|
| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q8_0.gguf) | Q8_0 | 0.9 | fast, best quality |
|
|
| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.f16.gguf) | f16 | 1.6 | 16 bpw, overkill |
|
|
|
|
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
types (lower is better):
|
|
|
|
 |