Zen Eco (open-weight tier)
Collection
Open-weight 'eco' tier — 4B instruct / thinking / agent. • 6 items • Updated
zen-eco-4b-agent (MLX)
MLX 4-bit build of the Eco 4B agent (tool-calling fine-tune), for Apple Silicon.
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 | MLX 4-bit |
Usage
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("zenlm/zen-eco-4b-agent-mlx")
messages = [{"role": "user", "content": "Hello, who are you?"}]
prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True)
print(generate(model, tokenizer, prompt=prompt, verbose=True))
License
apache-2.0. Upstream: Qwen/Qwen3-4B by Alibaba Qwen (apache-2.0).
- Downloads last month
- 156
Model size
0.6B params
Tensor type
BF16
·
U32 ·
Hardware compatibility
Log In to add your hardware
4-bit
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("zenlm/zen-eco-4b-agent-mlx") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True)