{"meta":{"count":1,"page":1,"pages":1,"per_page":12,"applied":{"engine":null,"model":null,"quant":null,"storage":null,"hardware":"radeon-ai-pro-r9700-x2","generation":null,"task":null,"tier":null,"tags":[],"vram":null,"search":null,"sort":"updated","featured":false},"origin":"https://localairecipes.com","openapi":"/openapi.json","updated_at":"2026-10-31T04:53:28+00:00"},"recipes":[{"slug":"qwen3-8-27b-paro-mxfp6-2x-radeon-ai-pro-r9700-vllm-radiance-tp2","title":"Qwen3.8-27B PARO-MXFP6 2x Radeon AI PRO R9700 \u2014 vLLM radiance TP2","summary":"27B Qwen served from a single podman-compose stack on two Radeon AI PRO R9700 (gfx1201) cards: vLLM runs the prebuilt stilldeadcode/vllm-radiance:0.9.3 image (RDNA4 patches + tuned kernels baked in) with a PARO prelude that applies the radiance source patches, hipcc-builds the ParoQuant kernels and swaps in a patched libr4d at every start. ParoQuant MXFP6 (E2M3, 6.25 bpw, W6A8) of the Swift fine-tune at tensor parallel 2, R4D attention, fp8 KV, 262144-token context, external DFlash2-FP8 drafter with 7 draft tokens. Caddy fronts the only published port with an internal-CA TLS OpenAI+Anthropic API; a sandboxed Hermes agent container egresses through Squid and never touches the host or LAN. Model ids qwen3.8-27b and swift-qwen3.8-27b-paro-mxfp6.","tier":"community","beta":false,"generation":"amd","decode_tok_s":138,"prefill_tok_s":3348,"updated_at":"2026-10-20 21:52:36.618781-06","commit_sha":"eeb81045e6312bd245e460da2277b6b8557f1059","content_hash":"7e8ac2b04a18ee509166698bd6ef1546224f7c51","votes":0,"credit":[{"name":"vinniefranco (podman compose stack, TLS/egress design, bench harness)","url":"https://github.com/vinniefranco/hermes-vllm-2x-r9700"},{"name":"hugypufy (PARO MXFP6 checkpoint + radiance-vllm-mxfp4 fork + published perf table)","url":"https://huggingface.co/hugypufy/Swift-Qwen3.8-27B-PARO-MXFP6"},{"name":"StillDeadcode (vllm-radiance image, radiance engine, libr4d)","url":"https://codeberg.org/StillDeadcode/vllm-radiance"},{"name":"tcclaviger (DFlash2-FP8 drafter)","url":"https://huggingface.co/tcclaviger/Qwen3.8-27B-DFlash2-FP8"}],"uploaded_by":"localai-recipes","measured":null,"links":{"self":"/api/v1/recipes/qwen3-8-27b-paro-mxfp6-2x-radeon-ai-pro-r9700-vllm-radiance-tp2.json","alternate":"/r/qwen3-8-27b-paro-mxfp6-2x-radeon-ai-pro-r9700-vllm-radiance-tp2"}}]}