skrodahl/qwen38-27B-dual-rtx5060

Easy local setup for Qwen3.8-27B Abliterated: 256K context and measured 240-300 tokens/s generation on an RTX 5090.

A llama.cpp fork with TurboQuant/TCQ KV cache, fused Qwen MTP speculative decoding, and multi-GPU long-context serving fixes.

Fastest validated sglang recipe for Qwen3.8-27B (AWQ-INT4 + DSpark) on RTX 3090s — 1×/2×/4× GPU presets, image+video, full benchmarks

Qwen3.8-27B EXL3 (4.00 bpw) + DFlash2 speculative decoding for ExLlamaV3, validated at 262k context on a 24 GB RTX 3090

Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.

Qwen3.8-Flash-Next on 2× RTX 3090: with 128 GB RAM up to 4,191 tok/s prefill · 111.5 tok/s decode (131K prompt), full 256K window at 2,865 tok/s; with 64 GB RAM 3,410 tok/s prefill · 84 tok/s decode. New: opt-in uncensored mode (runtime abliteration, no new weights).

Deployment kit: Qwen3.8-27B EXL3 3.5bpw target + DFlash2 EXL3 5.0bpw speculative draft — launcher, config, model cards

NInfer port for Qwen 3.8 27B on RTX 4090

Qwen3.8-27B on 16-32 GB Nvidia GPUs one-click install for Windows / Linux