Fused dequantized MLX model
Base lineage: Qwen/Qwen3.5-9B
Workshop branch lineage: v14 broad-benchmark daily-driver
Best fit: users who want the raw MLX export rather than the smaller 4-bit package

Base vs This Model

Internal workshop evals. These scores are project-specific and directional, not public leaderboard claims.

Eval	Base `Qwen3.5-9B-MLX-4bit`	Qwenjamin Franklin
`workbench_local_agent_smoke`	63/100	72/100
`full40`	309/400	325/400
`json_hard`	15/30	30/30
`parser_gate`	2/3, 1/3, 1/3	3/3, 3/3, 3/3
`code_smoke`	95/120	95/120
`false_smoke`	102/110	110/110
`tool_schema_canary`	50/175	106/175
`no_tool_leakage`	99/100	100/100

Usage

bash

python -m mlx_lm generate \
  --model stamsam/Qwenjamin_Franklin \
  --prompt "Write one complete TypeScript module and return only code." \
  --max-tokens 512 \
  --temp 0.0

Notes

This is the larger raw MLX export of the tuned branch.
For strict JSON or code-only tasks, use explicit output instructions in the prompt.
Verify important outputs before using them in high-stakes workflows.