LinkPocketAiHubResource
For researchers and developers running local AI pipelines on macOS, this provides an accessible 27B vision-language checkpoint free from standard safety refusals. The model card explicitly warns that abliteration does not equate to improved truthfulness and requires external output validation.
PocketAiHub provides detailed machine-readable validation and recipes for reproducibility. The benchmarks highlight the operational sweet spot: 4-bit and 6-bit variants retain full tool-calling and multimodal capabilities with manageable unified memory footprints, while extreme 2-bit quantization breaks core reasoning and tool use.
Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.
Similar in content, found by the AI search.
X post:Trevor Wood
Trevor Wood and PocketAI Model Lab have released MLX-optimised checkpoints of Qwen3.8-27B for Apple Silicon with built-in refusal mechanisms removed ('abliterated'), provided across multiple quantisation formats from 2-bit to BF16.
3.2kbookmarks199kviews
Link:OrcaRouter
OrcaRouter has released an abliterated, block-FP8 quantized version of the multimodal model Qwen3.8-27B on Hugging Face. By orthogonalising the internal refusal direction, standard safety guardrails were removed specifically for red-teaming, interpretability, and AI safety research.
Link:Qwen
The Qwen team has released Qwen3.8-27B, a compact, dense vision-language model under the Apache-2.0 licence. The 27-billion-parameter model pairs Gated DeltaNet with conventional gated attention, handles images and videos natively, and introduces flexible reasoning controls.
Link:Empero AI
Empero AI has released Qwythos-27B-v1, an open-weight reasoning model based on Qwen3.5-27B. The checkpoint preserves multi-token prediction (MTP), vision capabilities, and a 1M-token context window while specialising in terminal and agentic workflows.
Link:Unsloth AI
Unsloth AI has published Qwen3.6-27B-MTP-GGUF, providing quantized versions of the first open-weight model in the Qwen3.6 family. The 27-billion parameter multimodal model features Multi-Token Prediction (MTP) for accelerated inference alongside upgrades to agentic coding and tool calling.
Link:Unsloth AI
Unsloth AI has published GGUF quantizations for the Qwen3.8-27B model under an Apache-2.0 licence. Utilizing their new Dynamic V3.0 quantization format, Unsloth claims over 10% higher top-1 accuracy at identical sizes compared to alternative quants. Qwen3.8-27B is a 27-billion parameter dense vision-language model featuring native text, image, and video comprehension alongside granular thinking controls.
Parts of this content were created with the assistance of AI.
