Qwen/Qwen3-8B-MLX-bf16 - GGUF
This repo contains GGUF format model files for Qwen/Qwen3-8B-MLX-bf16.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b5753.
Our projects
Prompt template
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| Qwen3-8B-MLX-bf16-Q2_K.gguf | Q2_K | 3.282 GB | smallest, significant quality loss - not recommended for most purposes |
| Qwen3-8B-MLX-bf16-Q3_K_S.gguf | Q3_K_S | 3.770 GB | very small, high quality loss |
| Qwen3-8B-MLX-bf16-Q3_K_M.gguf | Q3_K_M | 4.124 GB | very small, high quality loss |
| Qwen3-8B-MLX-bf16-Q3_K_L.gguf | Q3_K_L | 4.431 GB | small, substantial quality loss |
| Qwen3-8B-MLX-bf16-Q4_0.gguf | Q4_0 | 4.775 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| Qwen3-8B-MLX-bf16-Q4_K_S.gguf | Q4_K_S | 4.802 GB | small, greater quality loss |
| Qwen3-8B-MLX-bf16-Q4_K_M.gguf | Q4_K_M | 5.028 GB | medium, balanced quality - recommended |
| Qwen3-8B-MLX-bf16-Q5_0.gguf | Q5_0 | 5.721 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| Qwen3-8B-MLX-bf16-Q5_K_S.gguf | Q5_K_S | 5.721 GB | large, low quality loss - recommended |
| Qwen3-8B-MLX-bf16-Q5_K_M.gguf | Q5_K_M | 5.851 GB | large, very low quality loss - recommended |
| Qwen3-8B-MLX-bf16-Q6_K.gguf | Q6_K | 6.726 GB | very large, extremely low quality loss |
| Qwen3-8B-MLX-bf16-Q8_0.gguf | Q8_0 | 8.710 GB | very large, extremely low quality loss - not recommended |
Downloading instruction
Command line
Firstly, install Huggingface Client
pip install -U "huggingface_hub[cli]"
Then, downoad the individual model file the a local directory
huggingface-cli download tensorblock/Qwen_Qwen3-8B-MLX-bf16-GGUF --include "Qwen3-8B-MLX-bf16-Q2_K.gguf" --local-dir MY_LOCAL_DIR
If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:
huggingface-cli download tensorblock/Qwen_Qwen3-8B-MLX-bf16-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'