Model Intelligence Sheet
ggml-org/Qwen3-8B-GGUF overview
Qwen3 8B Run it in the Llama app: https://llama.app Or from the terminal: bash llama serve hf ggml org/Qwen3 8B GGUF Source models https://huggingface.co/Qwen/…
Runs locally from ~1.04 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
6 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Qwen3-8B-BF16.gguf | GGUF | BF16 | 15.26 GB | Download |
| Qwen3-8B-Q8_0.gguf | GGUF | Q8_0 | 8.11 GB | Download |
| dflash-Qwen3-8B-BF16.gguf | GGUF | BF16 | 1.96 GB | Download |
| dflash-Qwen3-8B-Q8_0.gguf | GGUF | Q8_0 | 1.04 GB | Download |
| dspark-Qwen3-8B-BF16.gguf | GGUF | BF16 | 2.10 GB | Download |
| dspark-Qwen3-8B-Q8_0.gguf | GGUF | Q8_0 | 1.12 GB | Download |
Model Details
| Model ID | ggml-org/Qwen3-8B-GGUF |
|---|---|
| Author | ggml-org |
| Pipeline | text-generation |
| License | apache-2.0 |
| Base model | Qwen/Qwen3-8B |
| Last modified | 2026-10-19T15:35:31.000Z |
Model README
---
license: apache-2.0
pipeline_tag: text-generation
tags:
- gguf
- quantized
base_model:
- Qwen/Qwen3-8B
---
Qwen3-8B
Run it in the Llama app: https://llama.app
Or from the terminal:
llama serve -hf ggml-org/Qwen3-8B-GGUFSource models
- https://huggingface.co/Qwen/Qwen3-8B
- https://huggingface.co/z-lab/Qwen3-8B-DFlash-b16
- https://huggingface.co/deepseek-ai/dspark_qwen3_8b_block7
> [!IMPORTANT]
> This model is automatically converted using https://github.com/ggml-org/convert
Run ggml-org/Qwen3-8B-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models