Disclosure
This model is abliterated - the hard-refusal reflex on adult / creative content has been
reduced via single-direction weight orthogonalization. Harm guardrails are retained by design:
self-harm prompts still redirect to help (e.g. 988), and it is not intended to assist genuine
wrongdoing. This is a v1, partial abliteration; capability is preserved. Tagged
not-for-all-audiences. Use responsibly - you are responsible for your use. License inherited from
the base model: Apache-2.0.
Method
- Abliteration: single mid-layer refusal direction removed via weight orthogonalization on the
bf16 base; routers and the MTP/NextN block preserved.
- Format: safetensors, sharded, with config + tokenizer + index. MTP/NextN head preserved.
Files
Table with columns: Format, Precision, ~Size, Notes| Format | Precision | ~Size | Notes |
|---|
| safetensors (26 shards) | bf16 | ~67 GB | abliterated base; qwen35moe, MTP-preserved (41 blocks) |
The model is qwen35moe architecture with the MTP/NextN head at blk.40 preserved (41 blocks total),
~35B params with an A3B active-expert budget.
Quants
GGUF quants (Q6_K down to IQ2_M, MTP-preserved, imatrix-weighted) are published at
RobinsonLabs/Qwen3.6-35B-A3B-abliterated-GGUF.
Provenance
Qwen3.6-35B-A3B (Apache-2.0) -> abliterated bf16 (Robinson Labs). This safetensors repo is the
abliterated bf16 master; the GGUF ladder is quantized from it.