mlx-community / text-generation updated 2 years ago

Qwen2.5-Coder-7B-Instruct-4bit

The Model mlx-community/Qwen2.5-Coder-7B-Instruct-4bit was converted to MLX format from Qwen/Qwen2.5-Coder-7B-Instruct using mlx-lm version 0.18.1.

Params
1.2 B
Context
32,768
Downloads 30d
258 K
Likes
26
Commercial use: allowed apache-2.0 Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 24 days
259 K177 K
Aug 28Sep 5Sep 13Sep 20

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
model.safetensors u32 4.3 GB 5.4 GB ✅ Runs comfortably
model.safetensors (bf16, full) bf16 + 32K ctx 4.3 GB 5.9 GB ✅ Runs comfortably
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub
~ · curl · api/v1
$ curl -s https://aimodelscomparison.com/api/v1/models/qwen2-5-coder-7b-instruct-4bit
{
  "hf_id": "mlx-community/Qwen2.5-Coder-7B-Instruct-4bit",
  "params_b": 1.19,
  "context_length": 32768,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 258432,
  "vram_estimates": [
    { "quant": "u32", "gb": 5.4 }
  ],
  "updated_at": "2026-08-28T01:00:29Z"
}
est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture
Qwen2ForCausalLM
Parameters
1.2 B
Tensor type
U32
Context length
32,768
Vocabulary
152,064
Layers / heads
28 / 28
Licence
apache-2.0
First seen on the Hub
2024-09-18
Base model
Qwen2.5-Coder-7B
Training datasets
undisclosed
Added to our catalog
2026-08-28

Family

Base model and the most-downloaded derivatives in the catalog.

Compare with any text-generation model