{"meta":{"count":2,"page":1,"pages":1,"per_page":12,"applied":{"engine":null,"model":null,"quant":null,"storage":null,"hardware":["rtx-4090","rtx-5090-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":"2026-11-03T14:00:03+00:00"},"recipes":[{"slug":"qwen3-8-flash-next-iq3-s-mtp-on-1x-rtx-4090-llama-cpp-tandem-cpp","title":"Qwen3.8-Flash-Next IQ3_S + MTP on 1x RTX 4090 \u2014 llama.cpp + tandem.cpp MoE expert cache (ewhacc)","summary":"MoE expert-cache offload for llama.cpp via the tandem.cpp patch set: hot experts stay in a GPU expert cache, missed experts are split between CPU compute and an upload into the cache, sized from measured CPU and PCIe speeds; single-user decode is the target. Author's GSM8K first-200 decode numbers on the consumer PC (i5-12400F, 64 GB DDR4, RTX 4090 24 GB): Qwen3.8-Flash-Next IQ3_S + MTP 97.3 tok/s greedy and 96.1 sampled vs llama.cpp f5222f25c 29.8/29.4 (3.3x); gpt-oss-120b 51.5/48.0. REPRO CAVEAT: all numbers are author-self-reported on a repo <24h old with one commit day of history (initial commit 2026-11-02, no releases/tags); nothing reproduced on-box or by a third party - evidence is claimed, tier community. Requires CUDA 13.0-13.4 on Linux (sm_89/sm_120) and 64 GB host RAM for the 78 GiB IQ3_S weights; 1.4-2.1x gains on other MoE models that don't fit VRAM.","tier":"community","beta":false,"generation":"ada","decode_tok_s":73.7999999999999971578290569595992565155029296875,"prefill_tok_s":0,"updated_at":"2026-11-02 09:53:20.10132-07","commit_sha":"543df76dcb783c7c365b8ea88a2d81ed9d36de76","content_hash":"fd8e878ab3aa782deec1708f8b0913a0ee5ea7a7","votes":0,"credit":[{"name":"ewhacc - recipe, patch set and measurements","url":"https://github.com/ewhacc/tandem.cpp"},{"name":"llama.cpp / ggml (MIT)","url":"https://github.com/ggml-org/llama.cpp"},{"name":"MoE expert-split rule adapted from Strata (Niko1221)","url":"https://github.com/Niko1221/Strata"}],"uploaded_by":"localai-recipes","measured":null,"links":{"self":"/api/v1/recipes/qwen3-8-flash-next-iq3-s-mtp-on-1x-rtx-4090-llama-cpp-tandem-cpp.json","alternate":"/r/qwen3-8-flash-next-iq3-s-mtp-on-1x-rtx-4090-llama-cpp-tandem-cpp"}},{"slug":"glm-5-3-flash-exl3-2-05bpw-on-2x-rtx-5090-tabbyapi-hot-expert-sw","title":"GLM-5.3-Flash EXL3 2.05bpw on 2x RTX 5090 - TabbyAPI hot-expert swaps, 262K ctx, vision","summary":"GLM-5.3-Flash (321B MoE, ~18B active) turboderp EXL3 2.05bpw on two RTX 5090 + 64 GB DDR5: TabbyAPI on ExLlamaV3 with CPU-offloaded routed experts (96/layer GPU0 layers 3-22+MTP, 102/layer GPU1 23-44), runtime hot-expert swaps, per-GPU expert split, the DSA indexer's per-token rows in a fixed ring, live /metrics token counters, the expert-exchange clock handed to the first text MoE layer so swaps also run at 2-4 streams, MTP head drafting 1 tok/step single-stream, 262,144-token window on an 8-bit KV page pool (~1.6 GiB across 4), vision ON with tower linears pinned in host RAM. Exact-output: no expert skipped, every draft verified. Measured 2026-10-10 (R969, three fresh boots): c1 score 62.9 tok/s (code 59.9/prose 66.7/chat 68.5/html 64.8/edit 53.9), 2/3/4-stream sums 74.4/92.0/98.0. Nine in-repo overlays on the qwen3.8-flash-next-2x-rtx5090 base image.","tier":"community","beta":false,"generation":"blackwell","decode_tok_s":62.89999999999999857891452847979962825775146484375,"prefill_tok_s":2023,"updated_at":"2026-10-29 23:29:37.491895-06","commit_sha":"4dc491797af361a6a0f4cdedde5f7dbeb918082d","content_hash":"66ee933dc865f3362d1e2880b2ef8e330f331b05","votes":0,"credit":[{"name":"adrienbrault (recipe, five patch overlays, measurements)","url":"https://github.com/adrienbrault/glm5.3-flash-2x-rtx5090"},{"name":"zai-org (GLM-5.3-Flash)","url":"https://huggingface.co/zai-org/GLM-5.3-Flash"},{"name":"turboderp (EXL3 2.05bpw quantisation; ExLlamaV3 + CPU MoE offload)","url":"https://huggingface.co/turboderp/GLM-5.3-Flash-exl3"},{"name":"theroyallab (TabbyAPI)","url":"https://github.com/theroyallab/tabbyAPI"},{"name":"adrienbrault/qwen3.8-flash-next-2x-rtx5090 (base image: ExLlamaV3 dev 5783a93 patch stack + TabbyAPI 53da7919)","url":"https://github.com/adrienbrault/qwen3.8-flash-next-2x-rtx5090"}],"uploaded_by":"localai-recipes","measured":null,"links":{"self":"/api/v1/recipes/glm-5-3-flash-exl3-2-05bpw-on-2x-rtx-5090-tabbyapi-hot-expert-sw.json","alternate":"/r/glm-5-3-flash-exl3-2-05bpw-on-2x-rtx-5090-tabbyapi-hot-expert-sw"}}]}