Dsg2/Qwen3.5-4B-Pruned-Coder-UD-Q6_K_XL.gguf overview
Qwen3.5 4B Pruned Coder UD Q6 K XL: A pruned + quantization aware fine tuned coding agent Trimmed 17% of neurons. Light bench: | model | size | prefill t/s | d…
Runs locally from ~3.65 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Qwen3.5-4B-Pruned-UD-Q6_K_XL.gguf | GGUF | Q6_K_XL | 3.65 GB | Download |
Model Details
| Model ID | Dsg2/Qwen3.5-4B-Pruned-Coder-UD-Q6_K_XL.gguf |
|---|---|
| Author | Dsg2 |
| Pipeline | text-generation |
| License | apache-2.0 |
| Base model | unsloth/Qwen3.5-4B-GGUF |
| Last modified | 2026-06-21T08:40:54.000Z |
Model README
---
license: apache-2.0
datasets:
- Dsg2/CodeMix
language:
- en
base_model:
- unsloth/Qwen3.5-4B-GGUF
pipeline_tag: text-generation
tags:
- code
---
Qwen3.5-4B-Pruned-Coder-UD-Q6_K_XL: A pruned + quantization aware fine tuned coding agent
Trimmed 17% of neurons.
Light bench:
| model | size | prefill t/s | decode t/s | code | instruct | prose | tool |
|---|---|---|---|---|---|---|---|
| 4B base | 3.86 GiB | 11.1 | 4.77 | 3.13 | 2.52 | 1.73 | 8.16 |
| 4B-Pruned | 3.65 GiB | 12.2 | 5.51 | 3.51 | 2.81 | 9.32 | 5.82 |
Calibrated on ~63k code/instruct/tool call tokens for 2 CPU hours.
Run Dsg2/Qwen3.5-4B-Pruned-Coder-UD-Q6_K_XL.gguf with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models