Downloads · 30 days
16
12% of all-time downloads
shaffhausen/Qwen3.6-27B-Omnimerge-v4-MLX-4bit
Qwen3.6-27B-Omnimerge-v4-MLX-4bit is a text generation model from shaffhausen. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as apache-2.0.
4-bit MLX quantization of ManniX-ITA/Qwen3.6-27B-Omnimerge-v4 for native Apple Silicon inference via mlx-lm.
Downloads · 30 days
16
12% of all-time downloads
All-time downloads
134
Public
Parameters
26.9B
15.2 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors15.1 GB · 100%
How the weights are stored.
U3226.9B · 100%
From the Hugging Face model README
4-bit MLX quantization of ManniX-ITA/Qwen3.6-27B-Omnimerge-v4 for native Apple Silicon inference via mlx-lm.
The base model is a same-base DARE-TIES (Omnimerge_v2 method) merge of Qwen/Qwen3.6-27B with three Qwen3.6 fine-tunes (rico03, Esper3.1, kai-os Opus-Reasoning-anchor) plus an MLP-passthrough surgery that fixes Qwen3.6's reasoning-tag-emission fragility. Benchmark numbers and the full method writeup live on the base model card.
-q --q-bits 4)mlx_lm.convert quantizer)mlx==0.30.0 + mlx-cuda==0.30.0 + mlx-lm==0.30.7 on Linux + RTX 3090 (CUDA backend used only for the conversion step; end users run the native Apple Silicon MLX runtime, which has no CUDA dependency).Conversion recipe: omnimergekit/scripts/mlx_convert.sh — the canonical OmniMergeKit MLX-conversion runner. See MLX_CONVERT.md for the full pin rationale and disk-budget notes.
Tested with mlx-lm >= 0.30.7 on macOS (M1/M2/M3/M4):
pip install -U mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("ManniX-ITA/Qwen3.6-27B-Omnimerge-v4-MLX-4bit")
prompt = "Write a Rust function that returns the n-th Fibonacci number iteratively."
print(generate(model, tokenizer, prompt=prompt, max_tokens=512, verbose=True))
The base model emits Qwen3.6 reasoning tags (<think>...</think>); strip them in post-processing or use the chat template that wraps them appropriately.
Empirically (M-series, 32 GB+ recommended):
The vision tower is not included in the MLX export — this is a text-only build. For multimodal use, prefer the GGUF release with bartowski/Qwen_Qwen3.6-27B-GGUF's mmproj, or run BF16 via transformers.
ManniX-ITA/Qwen3.6-27B-Omnimerge-v4ManniX-ITA/Qwen3.6-27B-Omnimerge-v4-GGUFmannix/omnimerge-v4mann1x/omnimergekitApache 2.0 — inherits from Qwen3.6 base. See the base model card for the full attribution list (Qwen team, rico03, ValiantLabs, kai-os, mergekit community).