AEON-7/Qwen3.6-35B-A3B-heretic-NVFP4-DFlash

Qwen3.8-Flash-Next (NVFP4) on DGX Spark in vLLM: one Spark 43.9 tok/s with our disk-backed n-gram table patch, staged gather and reduced-vocab MTP draft; TP2 SPEED 53.7; TP4 CONTEXT 9M KV pool. Launchers, patch, 40-prompt harness, KV ledger, credits. SGLang TP2 day-0 lane kept.

Qwen3.8 Flash at 74 tok/s on a single DGX Spark / GB10. vLLM + MTP recipe, 212 tok/s at 8 streams.

Qwen3.5-122B-A10B on DGX Spark: 28.3 → 51 tok/s (+80%)

Fully uncensored, capability-enhanced abliteration of Qwen3.6-27B. NVFP4 + z-lab DFlash speculative decoding (n=12) on the unified ghcr.io/aeon-7/aeon-vllm-ultimate:latest container, tuned for long-context draft acceptance on DGX Spark. 6 HF variants (BF16/NVFP4/MTP/MTP-XS), docker-compose, and QuickStart.

recipe for running Qwen3.8-Flash-Next on a single DGX Spark

Qwen3.8 Flash Next on one DGX Spark (TensorFold)

qwen38-flash-next recipe for solo GB10

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

Run Qwen3.8-Flash-Next (180B) on a single DGX Spark by keeping its 51B n-gram embedding table on NVMe