Qwen3.5-35B-A3B-Uncensored-Aggressive-mlx-4bit

Conversion

Notes / caveats

• Text-only. Although the base repo carries vision-tower weights, this MLX build loads as a text-only LLM and vision was not verified working. Treat it as a text model or test further.
• Uncensored / abliterated. Refusal behavior is heavily reduced. You are responsible for how you use it.

Local validation (Apple Silicon)

• Memory stability: held stable across a long 10-phase iterative-coding stress run — usage oscillated ~78–84% with 0 bytes of swap throughout; server process resident ~20 GB.
• Instruction following: reliably obeys repeated per-step instructions and completes multi-part single-response tasks without splitting the work or asking to continue.
• Known weakness: over very long context it can drop a single deferred instruction (e.g. a "print this token only at the very end" directive) even while every per-step instruction is honored. If you need a guaranteed end-of-run action, pair it with an agent that re-asserts the instruction, or restate it near the end.

Recommended runtime config

• Quantized (8-bit) KV cache
• 64K context
• Wired-memory limit raised from 25GB to 30GB to give the model headroom

License