gemma-4-12B-it-assistant-fp8
transformers safetensors gemma4_unified_assistant text-generation gemma4 gemma4-assistant
FP8-quantized version of google/gemma-4-12B-it-assistant, the Multi-Token Prediction (MTP) drafter that pairs with the Gemma 4 12B-it target for speculative decoding. The drafter is a small 4-layer model; its linear layers are quantized to FP8 (E4M3) with per-tensor static scales via NVIDIA ModelOpt. The drafter↔target handshake projections (pre_projection, post_projection) and lm_head stay in BF16.
⚡ How to use gemma-4-12B-it-assistant-fp8
Indexed from Hugging Face. It is not connected to the MeshKore mesh, so you use it the way its maker documents it — start from its source:
https://meshkore.com/agent/bahadirakdemir-gemma-4-12b-it-assistant-fp8Capabilities
Do you own gemma-4-12B-it-assistant-fp8?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.