Yes — MULTIMODAL. Bundled mmproj.gguf (~928 MB, F16) preserves the full Qwen3.6-VL vision tower. Use it with llama-server --mmproj or llama-mtmd-cli for text + image inference.
Q4_K_M (4-bit K-quant medium, ~4.92 effective BPW) of a abliterated Qwen 3.6 27B v2 (the Jackrong Claude-Opus reasoning distill of Qwen 3.6 27B). Refusals reduced from 91/100 → 4/100 with KL drift of just 0.0176. By the Lemura Labs research team.
TL;DR
Property
Value
Disk size
~16 GB (15.4 GB LM + 928 MB mmproj)
BPW
~4.92 (Q4_K_M)
Scheme
llama.cpp Q4_K_M — super-block K-quantization with mixed Q4_K/Q6_K for attention-V and FFN-down. Industry-standard "best balance" quant — the most-downloaded GGUF format on HuggingFace.
Refusal rate (the ablation toolkit, n=100)
4/100 (vs vanilla Qwen 3.6 91/100)
KL divergence vs vanilla (at BF16)
0.0176
Vision
Yes — via paired mmproj.gguf
Recommended RAM/VRAM
24 GB+ Apple Silicon / 16 GB GPU
Runtime
stock ggml-org/llama.cpp (any recent build) — no custom fork needed for Q4_K_M.
Released by
Lemura Labs
All Qwen3.6-27B variants
The full Qwen3.6-27B family from Lemura Labs — same abliterated weights (refusal 4/100, KL 0.0176), different quant schemes for different runtimes.
1./build/bin/llama-cli \2 -m Qwen3.6-27B-V2-abliterated-uncensored-Q4_K_M.gguf \3 -ngl 99\4 -c 8192\5 --jinja \6 -p "Explain the difference between SSM and softmax attention in three sentences."
Ollama / LM Studio / Jan
Drop the two GGUF files into the runtime's models directory; standard multimodal flow.
Quantization details
Source weights: BF16 abliterated checkpoint (12 shards, ~50 GB) — the ablation toolkit T45 merged into Jackrong/Qwopus3.6-27B-v2.
Intermediate: F16 GGUF (53.8 GB, 851 tensors) produced by convert_hf_to_gguf.py from turbo-tan/llama.cpp-tq3.
Final quantization: see Step 4 above.
Vision projector: F16, 928 MB, shipped as mmproj-Qwen 3.6 27B-v2-abliterated-F16.gguf in this repo. Mandatory for image input; standard llama.cpp --mmproj flag.
Architecture notes
Qwen 3.6 27B uses a hybrid attention stack — 3 GatedDeltaNet (linear attention / SSM) layers followed by 1 full-softmax-attention layer, repeated 16× for 64 total layers; hidden 5120, vocab 248320, context 262144. The hybrid arch is supported in the turbo-tan/llama.cpp-tq3 fork (the upstream Qwen3_5ForConditionalGeneration registration). The SSM kernels run via llama.cpp's ssm_* tensor types.
Behavior caveats
Uncensored. Refusal directions were surgically removed; this model will answer prompts the parent would refuse. Use responsibly and within applicable law. The release is provided for safety research, red-teaming, and creative/educational use cases.
Multimodal preserved. Pair the LM GGUF with mmproj.gguf (in this repo) to get full vision input. Without mmproj, the model still loads as text-only.
Identity preserved. The model still self-identifies as Qwen (developed by Alibaba's Tongyi Lab) — abliteration does not rewrite factual self-knowledge.
Heavy chain-of-thought. Qwen 3.6 inherits Claude-Opus's verbose reasoning style. For terse answers, use a system prompt like "Be brief and direct. Skip your reasoning.".
