HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

Qwen3.6-27B-UD-MLX-3bit

unsloth/Qwen3.6-27B-UD-MLX-3bit

kind
mlx
quant
mlx
family
qwen
modality
image-text-to-text
root model
Qwen/Qwen3.6-27B
provider
unsloth
license
apache-2.0
language
—
context
262,144
library
mlx
vRAM (GB)
—
size on disk
—
downloads
1,098
likes
4
created
—
last modified
2026-04-23T06:30:26+00:00 (2026)
huggingface
https://huggingface.co/unsloth/Qwen3.6-27B-UD-MLX-3bit
tags
mlxsafetensorsqwen3_5unslothqwenimage-text-to-textconversationalbase_model:Qwen/Qwen3.6-27Bbase_model:quantized:Qwen/Qwen3.6-27Blicense:apache-2.03-bitregion:us

Benchmark scores (1)

benchmarkcategoryscorecontextconfevidence
Terminal-Benchagentic-coding2.0mediumTerminal-Bench 2.0

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.