Create prism-coder-2b model card (Qwen3.5-4B Q3_K_M, 99.1% BFCL)
Browse files
README.md
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: en
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
tags:
|
| 5 |
+
- tool-routing
|
| 6 |
+
- function-calling
|
| 7 |
+
- prism-coder
|
| 8 |
+
- qwen3.5
|
| 9 |
+
- synalux
|
| 10 |
+
- gguf
|
| 11 |
+
base_model: Qwen/Qwen3.5-4B
|
| 12 |
+
pipeline_tag: text-generation
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
# prism-coder:2b — iPhone / Mobile First Gate
|
| 16 |
+
|
| 17 |
+
Qwen3.5-4B quantized to Q3_K_M (2.3 GB) for on-device MCP tool routing on iPhone and mobile devices. Part of the [Prism Coder](https://ollama.com/dcostenco/prism-coder) fleet.
|
| 18 |
+
|
| 19 |
+
**99.1% routing accuracy** (BFCL, 115 cases × 3 seeds). Single failure: regex→knowledge_search edge case.
|
| 20 |
+
|
| 21 |
+
## Quick Start
|
| 22 |
+
|
| 23 |
+
```bash
|
| 24 |
+
ollama pull dcostenco/prism-coder:2b
|
| 25 |
+
```
|
| 26 |
+
|
| 27 |
+
## Download
|
| 28 |
+
|
| 29 |
+
| File | Size | BFCL | SHA256 |
|
| 30 |
+
|------|------|------|--------|
|
| 31 |
+
| [Qwen3.5-4B-Q3_K_M.gguf](https://huggingface.co/dcostenco/prism-coder-4b/resolve/main/Qwen3.5-4B-Q3_K_M.gguf) | 2.3 GB | 99.1% | `d6981ab4d77b...` |
|
| 32 |
+
|
| 33 |
+
The GGUF is hosted in the [prism-coder-4b](https://huggingface.co/dcostenco/prism-coder-4b) repo alongside the Q4_K_M variant.
|
| 34 |
+
|
| 35 |
+
## Why 2B?
|
| 36 |
+
|
| 37 |
+
This is a Qwen3.5-**4B** model quantized to Q3_K_M. The `2b` tag reflects its memory footprint (2.3 GB), not the parameter count. It fits in the same RAM as a 2B model while delivering 4B-class routing accuracy.
|
| 38 |
+
|
| 39 |
+
No fine-tuning — the system prompt IS the specialization, baked into the Ollama Modelfile.
|
| 40 |
+
|
| 41 |
+
## Fleet Position
|
| 42 |
+
|
| 43 |
+
| Model | Ollama tag | Size | BFCL | Role |
|
| 44 |
+
|---|---|---|---|---|
|
| 45 |
+
| **Qwen3.5-4B Q3_K_M** | **`prism-coder:2b`** | **2.3 GB** | **99.1%** | **iPhone / mobile** |
|
| 46 |
+
| Qwen3.5-4B Q4_K_M | `prism-coder:4b` | 3.4 GB | 100% | Verifier / 8 GB+ |
|
| 47 |
+
| prism-coder:14b | `prism-coder:14b` | 8.4 GB | 100% | Mac default |
|
| 48 |
+
| prism-coder:32b | `prism-coder:32b` | 16 GB | 100% | Complex tasks |
|
| 49 |
+
|
| 50 |
+
## Links
|
| 51 |
+
|
| 52 |
+
- [Ollama model page](https://ollama.com/dcostenco/prism-coder:2b)
|
| 53 |
+
- [GGUF download](https://huggingface.co/dcostenco/prism-coder-4b/resolve/main/Qwen3.5-4B-Q3_K_M.gguf)
|
| 54 |
+
- [Prism MCP Server](https://github.com/dcostenco/prism-coder)
|
| 55 |
+
- [Qwen3.5-4B base](https://huggingface.co/Qwen/Qwen3.5-4B)
|