qwen36

Qwen3.6 27B × DFlash — 30-35 tok/s on NVIDIA DGX Spark (GB10) - LLama.Cpp

Run Qwen3.6 35B-A3B MoE locally on a 6 GB VRAM laptop

Minimal C++ LLM Qwen/Gemma inference engine

Experimental DDTree-on-vLLM research track for Qwen3.6 AEON Ultimate on DGX Spark / GB10.

Enables small-to-large self-hosted ai models to use local source code when running tool-calling agentic workloads. We actively data mine 20,900+ (2+ TB) popular github repos using large and small ai models to create reuseable: json, markdown and parquet files for local-first tool-calling models.

Les 5 cercles + 18 stratégies d'optimisation tokens pour Qwen3.6+ (OpenRouter). Promptor v3 Council Edition : audit multi-perspective optionnel (5 advisors + peer review). Reverse Prompt Engineering. Python/PowerShell/OpenCode.

A local LLM inference framework, hand-tuned for the Ryzen AI Max APU. 3467 tok/s prefill, 76.7 tok/s decode on Qwen3.6-35B-A3B-FP8.

Run Qwen3.6-35B-A3B full native 258K context on 12GB VRAM (llama.cpp): ncmoe cliff rule, q4_0 KV prefill fix, 4 tuned profiles with scripts

Android port of Sonario for quickly summarizing YouTube videos, websites, documents, epubs & pasted text. Use qwen3.6-27b through Groq for fast free summaries, or run local LLMs for greater privacy.

Qwen3.6 27B MTP on Modal H100 with llama.cpp and an OpenAI-compatible API

Qwen3.6-27B at 111.6 tok/s (c4) on one DGX Spark—with FR-Spec, an x16 INT8 LM head, and 4.2× faster repeated-prefix TTFT.

Optimized Qwen3.6-35B-A3B recipe for DGX Spark — MTP Q4_0, 75-82 t/s