Qwen 3.6 35B-A3B
Overview
- 35B-parameter mixture-of-experts language model from the Qwen Series
- A3B routing variant activates ~3B parameters per token, maximizing throughput vs. memory tradeoffs
- Architecture: Sparse MoE with dense attention, optimized expert gating, and instruction-tuned reasoning/code capabilities
- Training: Multilingual corpus, heavy code synthesis, aligned for complex tool-use and long-context retention
Specialized Variants: Qwopus Coder
- Qwopus 3.6-35B-A3B-Coder: A specialized derivative developed by Jackrong, built on the Qwen 3.6-35B A3B base
- Agentic Self-Correction: Features “thinking-off” capabilities for improved code generation and debugging workflows
FableVibes 14B Variant
- FableVibes 14B: A fine-tuned variant of the Qwen 3.6-35B A3B architecture, optimized for specific local inference benchmarks
- Performance Context: Evaluated against the base 35B model in a 16GB VRAM setup to assess intelligence and performance trade-offs in constrained environments
- Analysis: See FableVibes 14B (Qwen) vs. 35B Base: Local LLM Performance and Intelligence for detailed benchmarking results by Luke’s Dev Lab
- Source: FableVibes 14B (Qwen) vs. 35B Base: Local LLM Performance and Intelligence