llama32-1b-cpu / README.md
LBJLincoln's picture
feat(llm-fleet): deploy 3 quantized CPU LLM Spaces (Qwen2.5-0.5B + Llama-3.2-1B + Gemma-2-2B) + gateway wiring
bfaf3ea
|
Raw
History Blame Contribute Delete
556 Bytes
---
title: Nomos42 Llama-3.2-1B CPU
emoji: 🦙
colorFrom: green
colorTo: blue
sdk: docker
app_port: 7860
pinned: false
hardware: cpu-basic
license: apache-2.0
---
# Nomos42 Llama-3.2-1B CPU
Pure FastAPI OpenAI-compatible inference server for **Llama-3.2-1B-Instruct** (GGUF Q4_K_M, ~800 MB) on HF Spaces free CPU tier. Used by the Nomos42 trading floor and llm-gateway as a zero-quota self-hosted fallback.
- `GET /` -> `{model, ready, ...}`
- `GET /v1/models`
- `POST /chat/completions` (OpenAI schema)
- `POST /v1/chat/completions` (OpenAI schema)