VertexResearch/Vertex-0.6-15M-Base-GGUF overview
Vertex 0.6 15M Base Base pretrain only checkpoint of Vertex 0.6 15M , a tiny ~15M param model from the Vertex 0.6 family. Qwen3 architecture: hidden 256, 10 la…
Runs locally from ~29.2 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Vertex-0.6-15M-Base-F16.gguf | GGUF | F16 | 29.2 MB | Download |
Model Details
| Model ID | VertexResearch/Vertex-0.6-15M-Base-GGUF |
|---|---|
| Author | VertexResearch |
| Pipeline | text-generation |
| License | apache-2.0 |
| Base model | VertexResearch/Vertex-0.6-15M-Base |
| Last modified | 2026-09-06T10:20:49.000Z |
Model README
---
license: apache-2.0
datasets:
- openbmb/Ultra-FineWeb
- openbmb/Ultra-FineWeb-L3
language:
- en
pipeline_tag: text-generation
base_model: VertexResearch/Vertex-0.6-15M-Base
base_model_relation: quantized
tags:
- tiny
- vertex
---
Vertex 0.6 15M Base
Base (pretrain-only) checkpoint of Vertex 0.6 15M, a tiny ~15M-param
model from the Vertex 0.6 family. Qwen3 architecture: hidden 256, 10 layers,
4 heads / 2 KV (GQA, head_dim 64), SwiGLU ffn 1024, 20000-vocab ByteLevel
BPE, tied embeddings, ctx 2048.
Pretrained from scratch on 12B tokens of English web text: Ultra-FineWeb
plus Ultra-FineWeb-L3 synthetic rewrites (Multi-Style + QA), ~800 tokens per
parameter, on a single RTX 4060 Laptop (8GB).
This is a raw language model — no chat template, no instruction tuning. For chat, see
Training data
Pretrained on English web text from openbmb/Ultra-FineWeb and openbmb/Ultra-FineWeb-L3 (Multi-Style + QA synthetic configs), 12B tokens total.
Run VertexResearch/Vertex-0.6-15M-Base-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models