20+ models
Qwen3.6 delivers substantial upgrades in agentic coding and thinking preservation than previous Qwen models.
pulled as BF16, vocab slice (combined_en_huge) requant to IQ4_NL (combined_en_huge) -- (English + Coding focus) - ~20% faster than Q4_K_M
Qwen3.6-35b-a3b-abliterated-nvfp4-mtp-mlx
https://huggingface.co/tvall43/Qwen3.6-14B-A3B-VibeForged-v2-GGUF
Mixed-precision quant of Qwen3.6-35B-A3B: 8-bit attention, 4-bit experts.
Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-fulluncen
Abliterated (uncensored) version of **Qwen/Qwen3.6-27B**, refusal behavior reduced via targeted weight modification with the Heretic library, while preserving coherence.
Qwen3.6-35B uncensored flagship: 1M certified 70/70, vision, MTP grafted. One file, four capabilities.
A custom model built on Qwen3.6-35B-A3B (abliterated), tuned to act as an autonomous coding and administration agent. It speaks the Anthropic-compatible API, so it drives Claude Code fully locally — your code never leaves your machine.
Pruned to 184e version of 35b-a3b with LCB and MultiPL-E HE targeting for Coding
Qwen3.6-35B-A3B MoE coding agent for Claude Code / Codex / opencode, 64K context, native tool-calling, honest tool use, safety guardrails intact
0/465 refusals. Fully uncensored with zero capability loss.
Q4-K-M based on lordx64/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled