| --- |
| language: en |
| license: apache-2.0 |
| tags: |
| - tool-routing |
| - function-calling |
| - prism-coder |
| - qwen3.5 |
| - synalux |
| - qlora |
| - gguf |
| base_model: Qwen/Qwen3.5-9B |
| pipeline_tag: text-generation |
| --- |
| |
| # prism-coder:9b — Prism Memory Tool Router (Default Tier) |
|
|
| QLoRA fine-tuned [Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B) for MCP tool routing in the [Prism Coder](https://ollama.com/dcostenco/prism-coder) system. Replaces the previous 14B tier with 36% smaller footprint and higher accuracy. |
|
|
| ## Quick Start |
|
|
| ```bash |
| ollama pull dcostenco/prism-coder:9b |
| ``` |
|
|
| ## BFCL Benchmark — 100% × 3 seeds |
|
|
| **64/64 × 3 shuffled runs = 100.0%, 0 hallucinations** |
|
|
| | Category | Count | Accuracy | |
| |----------|------:|:--------:| |
| | simple | 10 | 100% | |
| | relevance_detection | 10 | 100% | |
| | hallucination | 10 | 100% | |
| | disambiguation | 8 | 100% | |
| | format_sensitivity | 5 | 100% | |
| | ast_parameter | 5 | 100% | |
| | edge_case | 8 | 100% | |
| | multi_turn_chain | 8 | 100% | |
|
|
| ### vs Previous 14B (Qwen 3) |
|
|
| | Metric | 14B (Qwen 3) | 9B (Qwen 3.5) | |
| |---|---|---| |
| | BFCL Overall | 90.3% | **100.0%** | |
| | Model Size | 9.0 GB | **5.8 GB** | |
| | Hallucinations | 0 | 0 | |
|
|
| ## Training |
|
|
| - **Method**: QLoRA (4-bit base + bf16 adapters) on Apple Silicon M5 48GB |
| - **Base**: `mlx-community/Qwen3.5-9B-MLX-4bit` for training, `Qwen/Qwen3.5-9B` bf16 for merge |
| - **LoRA**: rank=32, alpha=64, 16 layers |
| - **Corpus**: 26K rows (40% AAC / 12% abstention / 12% safety / 36% tool-use) |
| - **Iterations**: 2000 at LR 1e-4 |
| - **Layer 3**: Inference-time rules for tool remapping, param normalization, multi-turn chain parsing |
|
|
| ## Architecture |
|
|
| Qwen3.5-9B uses a hybrid attention architecture: |
| - **Linear attention layers** (Gated DeltaNet) — O(n) inference, pattern matching |
| - **Full attention layers** (standard softmax) — precise retrieval and reasoning |
|
|
| ## Fleet Position |
|
|
| | Model | Ollama tag | Size | BFCL | Role | |
| |---|---|---|---|---| |
| | Qwen3.5-2B Q3_K_M | `dcostenco/prism-coder:2b` | 2.3 GB | 99.1% | iPhone / mobile | |
| | Qwen3.5-4B Q4_K_M | `dcostenco/prism-coder:4b` | 3.4 GB | 100% | Verifier / 8 GB+ | |
| | **Qwen3.5-9B Q4_K_M** | **`dcostenco/prism-coder:9b`** | **5.8 GB** | **100%** | **Default router** | |
| | prism-coder:32b | `dcostenco/prism-coder:32b` | 19 GB | 100% | Complex tasks | |
|
|
| ## Links |
|
|
| - [Ollama model page](https://ollama.com/dcostenco/prism-coder) — pull and run |
| - [Prism MCP Server](https://github.com/dcostenco/prism-coder) — the MCP server |
| - [Qwen3.5-9B base](https://huggingface.co/Qwen/Qwen3.5-9B) — upstream model |
|
|
