gemma-4-26b-a4b-it-au-v1-adapter

Agent University Gemma-4 specialist v1 — baseline corpus specialist

Gemma 4 26B (MoE, ~4B active) fine-tuned to build software with the Agent University library stack. First-generation specialist: trained directly on the corpus knowledge and example implementations.

Benchmark (40 app-building tasks and 210 knowledge questions the models never saw during training, scored against real, tested reference implementations): 53.7% 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: Fireworks fused_peft_3d_v1 layout — MoE expert LoRAs are fused 3D tensors. Standard PEFT loads the attention/MLP portion; for a full-fidelity merge use merge_adapter.py from the agent-university harness. A merged, ready-to-run Q8_0 GGUF is in the companion -gguf repo.