GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

dennisonb/gemma-4-26b-a4b-it-au-v3-gguf overview

Agent University Gemma 4 specialist v3 — recall drills + more tasks Adds exact identifier recall drills and 6× more implementation tasks to the v2 recipe. Benc…

ggufloragemma-4code-specialistagent-universitybase_model:google/gemma-4-26B-A4B-itbase_model:adapter:google/gemma-4-26B-A4B-itlicense:apache-2.0endpoints_compatibleregion:us

Runs locally from ~25.02 GB disk (32 GB+ VRAM class GPUs with llama.cpp / guIDE).

Downloads
0
Likes
0
Pipeline
Author

Repository Files & Downloads

1 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
tuned-v3-q8.ggufGGUFQ825.02 GBDownload

Model Details

Model IDdennisonb/gemma-4-26b-a4b-it-au-v3-gguf
Authordennisonb
Pipeline
Licenseapache-2.0
Base modelgoogle/gemma-4-26B-A4B-it
Last modified2026-07-05T16:54:08.000Z

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 v3 — recall drills + more tasks

Adds exact-identifier recall drills and 6× more implementation tasks to the v2 recipe.

Benchmark (40 app-building tasks and 210 knowledge questions the models never saw during training, scored against real, tested reference implementations): 53.3% on build tasks; best exact-fact retention of the SFT-only line (21.4%). 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 -adapter repo.

Run dennisonb/gemma-4-26b-a4b-it-au-v3-gguf with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models