Model Intelligence Sheet
jdluzen/Qwen3-Coder-Next-Eagle3-GGUF overview
GGUF quants for thoughtworks/Qwen3 Coder Next Eagle3 https://huggingface.co/thoughtworks/Qwen3 Coder Next Eagle3 Current status: sort of works, not available i…
Runs locally from ~67.9 MB 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 |
|---|---|---|---|---|
| Model-145M-BF16.gguf | GGUF | BF16 | 282.9 MB | Download |
| Model-145M-MXFP4_MOE.gguf | GGUF | GGUF | 153.1 MB | Download |
| Model-145M-Q1_0.gguf | GGUF | Q1_0 | 67.9 MB | Download |
| Model-145M-Q3_K_M.gguf | GGUF | Q3_K_M | 93.0 MB | Download |
| Model-145M-Q4_K_M.gguf | GGUF | Q4_K_M | 104.6 MB | Download |
| Model-145M-Q8_0.gguf | GGUF | Q8_0 | 153.1 MB | Download |
Model Details
Model README
---
license: apache-2.0
base_model:
- thoughtworks/Qwen3-Coder-Next-Eagle3
---
GGUF quants for thoughtworks/Qwen3-Coder-Next-Eagle3
Current status: sort of works, not available in mainline llama.cpp yet.
Run jdluzen/Qwen3-Coder-Next-Eagle3-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models