Model Intelligence Sheet
tunedtensor/email-triage-v1-gguf overview
Email Triage v1 GGUF This repository contains the Q5 K M GGUF build of Tuned Tensor Email Triage v1 for llama.cpp. Files email triage v1 Q5 K M.gguf : quantize…
Runs locally from ~1.31 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
1 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| email-triage-v1-Q5_K_M.gguf | GGUF | Q5_K_M | 1.31 GB | Download |
Model Details
| Model ID | tunedtensor/email-triage-v1-gguf |
|---|---|
| Author | tunedtensor |
| Pipeline | — |
| License | other |
| Base model | Qwen/Qwen3.5-2B |
| Last modified | 2026-06-28T06:46:57.000Z |
Model README
---
license: other
base_model: Qwen/Qwen3.5-2B
tags:
- gguf
- llama.cpp
- triage
- tuned-tensor
model_name: Email Triage v1 GGUF
---
Email Triage v1 GGUF
This repository contains the Q5_K_M GGUF build of Tuned Tensor Email Triage v1 for llama.cpp.
Files
email-triage-v1-Q5_K_M.gguf: quantized GGUF for local inference.
Source Model
- Tuned Tensor model ID:
86fd9d01-87b8-4c34-ad70-c4264cd35eee - Tuned Tensor run ID:
1f75d0b7-f818-4f0e-94a8-58d64fd0e41e - Base model:
Qwen/Qwen3.5-2B - Dataset:
tunedtensor/email-triage-v1
Output Schema
The model is intended to return compact strict JSON with:
triage:reply,archive,escalate,ignore, orreviewpriority:low,normal,high, orcriticalshould_process: booleanconfidence: number from 0 to 1summary: concise content summaryreason: short triage rationale
For best results with llama.cpp, use JSON-schema constrained decoding as implemented by the email-triage CLI.
Run tunedtensor/email-triage-v1-gguf with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models