| --- |
| base_model: Qwen/Qwen3.5-9B |
| library_name: mlx |
| pipeline_tag: text-generation |
| license: apache-2.0 |
| tags: |
| - mlx |
| - qwen3.5 |
| - qwenjamin-franklin |
| - dequantized |
| - local-first |
| - text-generation |
| --- |
| |
|  |
|
|
| # Qwenjamin Franklin |
|
|
| Qwenjamin Franklin is the dequantized raw MLX export of the same tuned `v14` branch used for the 4-bit release. |
|
|
| This repo is for people who want the larger raw MLX artifact from the same local workshop line instead of the compact 4-bit build. |
|
|
| ## What This Release Is |
|
|
| - 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. |
|
|
