Skip to content
#

flash-next

Star

Here are 2 public repositories matching this topic...

youssofal / MTPLX

Star 2.5k

The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenAI and Anthropic compatible local server.

macos metal mtp mlx inference-engine apple-silicon local-llm llm-inference local-ai qwen speculative-decoding openai-compatible claude-code qwen3-next anthropic-compatible native-mtp mtplx qwen3-8 qwen3-8-flash-next flash-next
  • Updated Oct 3, 2026
  • Python

lifeidle / qwen3.8-flash-next-strata-5090-laptop-24gb

Star 16

Qwen3.8-Flash-Next 177B MoE (ISTA GSQ-RCO IQ3_XXS) self-hosted on RTX 5090 Laptop (24GB VRAM + 64GB RAM) via Strata: up to 110 tok/s (100+ sustained), 256K full context, vision, MTP speculative decoding, reasoning default xhigh (max tier). GPU+CPU both saturated. 26 measured rounds, 7 quant tiers screened. 中英双语实测实录

self-hosted moe strata quantization mtp reasoning vision-language-model local-llm gguf speculative-decoding rtx5090 qwen3 qwen38 256k-context flash-next iq3-xxs
  • Updated Oct 5, 2026
  • Python

Add this topic to your repo

To associate your repository with the flash-next topic, visit your repo's landing page and select "manage topics."

Learn more