dennisonb/gemma-4-26b-a4b-it-au-v2-gguf overview
Agent University Gemma 4 specialist v2 — augmented training Same specialist goal as v1 with 3× question phrasing augmentation and a 4× larger adapter rank 32 .…
Runs locally from ~25.02 GB disk (32 GB+ VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| tuned-v2-q8.gguf | GGUF | Q8 | 25.02 GB | Download |
Model Details
Model README
---
license: apache-2.0
base_model: google/gemma-4-26B-A4B-it
tags:
- lora
- gemma-4
- code-specialist
- agent-university
---
Agent University Gemma-4 specialist v2 — augmented training
Same specialist goal as v1 with 3× question-phrasing augmentation and a 4× larger adapter (rank 32).
Benchmark (40 app-building tasks and 210 knowledge questions the models never saw during training, scored against real, tested reference implementations): 52.4% correct library-API usage on unseen build tasks. For comparison, Claude Sonnet 5 scored 31.5% on the same build tasks.
- Base:
google/gemma-4-26B-A4B-it(Apache-2.0, subject to Gemma Terms) - Training: LoRA supervised fine-tuning on the Agent University corpus — ~90 live-tested curricula for AI/agent libraries and dev tools (Supabase, MCP, Next.js, Cloudflare, Slack, and more)
- Format: Merged Q8_0 GGUF — runs directly with llama.cpp / LM Studio / Ollama. The raw LoRA adapter is in the companion
-adapterrepo.
Run dennisonb/gemma-4-26b-a4b-it-au-v2-gguf with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models