1.Niko1221 / Strata
Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
+4,739 stars
from 34,556 · score 8.46
Trending repositories
Ranked by Attention Score: stars gained over the last 7 complete days
19 repositories by Attention Score · Oct 28, 2026 – Nov 3, 2026 (UTC)
+730 stars
from 132,565 · score 6.59
+263 stars
from 10 · score 5.58
4.jesdga95 / basalt
Local inference engine for Qwen3.8-Flash-Next on NVIDIA Blackwell
+244 stars
from 264 · score 5.50
5.simplexai-labs / PolyStrata
Run large AI models on your own PC: Qwen3.8-Flash-Next on Strata's engine, and GLM 5.3 Flash, DeepSeek V4 Flash, LFM2.5, Qwen3.6, Ornith 1.5, Gemma 4, Tiel Coder and MiniCPM-V on a second engine written for PolyStrata. One-click install for Windows and Linux, OpenAI/Anthropic API on localhost.
- anthropic-api
- cuda
- gemma
- gguf
- glm
- inference-engine
- +7 more
+234 stars
from 574 · score 5.46
+197 stars
from 41,259 · score 5.29
7.incoai / splash
A local inference engine for Apple silicon, built around the model.
- apple-silicon
- coding-agents
- llm-inference
- macos
- metal
- speculative-decoding
+171 stars
from 1,886 · score 5.15
8.Soulmate-Halo / heterogeneous-gpu-pd-lab
TranslatedUsing dense-compute cards to accelerate sparse, large-VRAM hosts, where the hosts include AI Max+ 395, M3 512G, DGX Spark, and others.
- llama-cpp
- pipeline-parallelism
- prefill-decode
- rtx-3060
- strix-halo
- heterogeneous-gpu
+107 stars
from 979 · score 4.68
9.nace-ai / kapitsa
Blazing fast Apple Silicon inference engine optimized for Qwen & Nemotron. OpenAI + Anthropic API compatible. Built by folks from nace.ai
+103 stars
from 523 · score 4.64
10.gufo-org / gufo
The Open Source Strix Halo AI engine. Qwen 3.8 Flash Next Q4_K_XL: 1,801.01 pp, 73.17 tg single user, 194.37 tok/s 8 users; Qwen 3.8 27B Q4_K_XL: 656.33pp, 70.56tg tok/s single user with DFlash2
- amd
- llm
- strix-halo
- gfx1151
- ryzen-ai
+93 stars
from 964 · score 4.54
11.cobanov / PS5LM
llama.cpp on a jailbroken PS5: run any GGUF model natively on the console, starting with Qwen 3.8
+79 stars
from 724 · score 4.38
12.Indras-Mirror / Xolotl
Xolotl (formerly Strata-DSV4.1): run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 90 GB RAM) at up to ~27 tok/s, 512K context, October 1017 builds included. Plus GLM-5.3-Flash and Qwen3.8. MoE experts tiered across VRAM, pinned RAM and NVMe; OpenAI + Anthropic API.
- cuda
- deepseek
- deepseek-v4
- gguf
- glm
- llm-inference
- +7 more
+72 stars
from 382 · score 4.29
13.mozilla-ai / llamafile
Distribute and run LLMs with a single file.
- cross-platform
- gguf
- llama-cpp
- local-ai
- local-inference
- local-llm
- +3 more
+53 stars
from 26,502 · score 3.99
14.IPADS-SAI / Mobiinfer-Android
MobiInfer runs 35B-A3B-class MoE models fully on-device on the Qualcomm Hexagon NPU, streaming experts from flash with lookahead scheduling (LES) and DSpark speculation.
+12 stars
from 192 · score 2.56
15.heterodoxin / AbliteratedOutTheBox
llama.cpp fork that abliterates at inference
+11 stars
from 154 · score 2.48
16.uxlfoundation / oneDNN
Open-source library of optimized deep learning operations (matmul, convolution, attention) for CPUs (x64, AArch64, RISC-V) and Intel GPUs. Used by PyTorch, TensorFlow, OpenVINO, and ONNX Runtime.
- onednn
- oneapi
- performance
- cpp
- x64
- aarch64
- +14 more
+7 stars
from 4,080 · score 2.08
17.IvanMurzak / Unreal-MCP
AI Game Developer for Unreal Engine — MCP plugin (C++ editor plugin + .NET bridge), unreal-cli, connects Unreal Editor to AI agents via ai-game.dev or a local MCP server
- ai
- ai-tools
- gamedev
- mcp
- mcp-server
- unreal
- +14 more
+6 stars
from 51 · score 1.95
18.VectorDB-NTU / RaBitQ-Library
Official library for RaBitQ vector quantization and approximate nearest-neighbor search, in C++ and Python.
- nearest-neighbor-search
- quantization
- vector-database
- vector-search
- ann
- approximate-nearest-neighbor-search
- +7 more
+2 stars
from 291 · score 1.10
19.google / minja
A minimalistic C++ Jinja templating engine for LLM chat templates
+1 stars
from 235 · score 0.69