zenlm/zen-eco-4b-agent-gguf overview
zen eco 4b agent GGUF GGUF build of the Eco 4B agent tool calling fine tune , for llama.cpp / LM Studio. Repackaged from Qwen/Qwen3 4B https://huggingface.co/Q…
Runs locally from ~5.7 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| zen-eco-3b-agent-f16.gguf | GGUF | F16 | 5.75 GB | Download |
| zen-eco-3b-agent-q4_k_m.gguf | GGUF | Q4_K_M | 1.80 GB | Download |
| zen-eco-3b-agent-q5_k_m.gguf | GGUF | Q5_K_M | 2.07 GB | Download |
| zen-eco-3b-agent-q8_0.gguf | GGUF | Q8_0 | 3.06 GB | Download |
| zen-eco-4b-agent-Q2_K.gguf | GGUF | Q2_K | 1.55 GB | Download |
| zen-eco-4b-agent-Q4_K_M-fixed.gguf | GGUF | Q4_K_M | 5.7 MB | Download |
| zen-eco-4b-agent-Q4_K_M.gguf | GGUF | Q4_K_M | 5.7 MB | Download |
| zen-eco-4b-agent-Q5_K_M.gguf | GGUF | Q5_K_M | 5.7 MB | Download |
| zen-eco-4b-agent-Q8_0.gguf | GGUF | Q8_0 | 5.7 MB | Download |
| zen-eco-4b-agent-f16.gguf | GGUF | F16 | 7.50 GB | Download |
Model Details
| Model ID | zenlm/zen-eco-4b-agent-gguf |
|---|---|
| Author | zenlm |
| Pipeline | text-generation |
| License | apache-2.0 |
| Base model | Qwen/Qwen3-4B |
| Last modified | 2026-07-14T09:10:17.000Z |
Model README
---
license: apache-2.0
base_model: Qwen/Qwen3-4B
pipeline_tag: text-generation
library_name: gguf
language:
- en
tags:
- text-generation
- gguf
- agent
- zen
- zenlm
- hanzo
---
zen-eco-4b-agent (GGUF)
GGUF build of the Eco 4B agent (tool-calling fine-tune), for llama.cpp / LM Studio.
Repackaged from Qwen/Qwen3-4B (apache-2.0, Alibaba Qwen). Not trained from scratch — a permissively-licensed redistribution for the OSS-clean Zen model line.
Specs
| Property | Value |
|----------|-------|
| Parameters | 4B (dense) |
| Architecture | Qwen3 (Qwen3ForCausalLM) |
| Format | GGUF (F16) |
Usage
# llama.cpp
./llama-cli -m zen-eco-4b-agent-f16.gguf -p "Who are you?" -n 50zen-eco-4b-agent-f16.gguf (F16) is provided. Load directly in LM Studio or any llama.cpp runtime.
License
apache-2.0. Upstream: Qwen/Qwen3-4B by Alibaba Qwen (apache-2.0).
Run zenlm/zen-eco-4b-agent-gguf with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models