ABEJA-Qwen3-14B-Agentic-256k-v0.1-MLX-8bit
mlx-community/ABEJA-Qwen3-14B-Agentic-256k-v0.1-MLX-8bit
Text generation · mlx
8-bit Open on Hugging Face
Parameters
15B
Weights (est.)
≈ 15.7 GB
Mac memory (est.)
24 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/ABEJA-Qwen3-14B-Agentic-256k-v0.1-MLX-8bit --prompt "Hello"
Details
- Base model
- abeja/ABEJA-Qwen3-14B-Agentic-256k-v0.1 (quantized)
- Vendor
- abeja
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- apache-2.0
- Downloads
- 69 in the last 30 days · 764 all time · 1 likes
- Published
- 2026-03-28 · updated 2026-03-28 (7mo ago)
- Languages
- ja
- Tags
- qwen3
Other MLX builds of abeja/ABEJA-Qwen3-14B-Agentic-256k-v0.1
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| ABEJA-Qwen3-14B-Agentic-256k-v0.1-MLX-4bit | 4-bit | ≈ 8.3 GB | 16 GB+ | 72 |
| ABEJA-Qwen3-14B-Agentic-256k-v0.1-MLX-8bit (this one) | 8-bit | ≈ 15.7 GB | 24 GB+ | 69 |