128k-context

Here are 3 public repositories matching this topic...

Alvinpro / Deploy-Local-Llama-C1-Qwen-3.8-27B-3090-24GB-Windows-11

One-click deployment of Qwen3.8-27B on a single RTX 3090 (24GB) on Windows 11: Q4_K_XL quantization + MTP speculative decoding + 128K context window, exposed as an OpenAI-compatible llama-server, averaging ~47 tok/s with ~1.5× lossless MTP speedup

deployment windows-11 local-llm rtx-3090 24gb qwen-38-27b 128k-context

Updated Aug 20, 2026
PowerShell

kutaelee / qwen38-flash-next-5090-128k-runtime-recipe

Star

Validated Qwen3.8-Flash-Next 128K WSL2 runtime recipe for a single RTX 5090.

wsl2 llama-cpp local-llm qwen rtx-5090 128k-context

Updated Aug 30, 2026
PowerShell

47thtechcorner / RayCodes_MiniCPM5_2B

Star

MiniCPM5-2B IS INSANE! 128K Context & Deep Reasoning Runs Locally - OpenBMB MiniCPM5-2B local execution and context benchmarking

pytorch huggingface local-ai deep-reasoning hybrid-reasoning openbmb 128k-context minicpm5-2b

Updated Sep 8, 2026
Python

Add this topic to your repo

To associate your repository with the 128k-context topic, visit your repo's landing page and select "manage topics."

Learn more