Qwen4-Exp (Qwen3.8-Flash-Next) SWA + MTP + PLE-on-iswa — bounded deep-context decode w/ long-range recall, TBQ4 4.25 bpv KV, DSpark + RotorQuant. Main (master) = Qwen4-Exp build; the Qwen35 SWA hybrid lives on the qwen35 branch. RTX 4090.
☆95Sep 24, 2026Updated last month
Alternatives and similar repositories for llama.cpp-turboq-mtp
Users that are interested in llama.cpp-turboq-mtp are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆151Jun 13, 2026Updated 4 months ago
- KVarN, KV cache precision tail, low-bit quants in llama.cpp for longer context of better precision in the same VRAM☆1,179Updated this week
- llama.cpp fork with TurboQuant WHT-rotated KV cache & weight compression + Gemma 4 MTP and Qwen 3.6 NextN speculative decoding (+30-50% t…☆433Updated this week
- LLM inference in C/C++☆57Oct 24, 2026Updated last week
- LLM inference in C/C++☆2,440Oct 22, 2026Updated last week
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Hindsight Memory for Open WebUI☆18May 27, 2026Updated 5 months ago
- AdaLLM is an NVFP4-first inference runtime for Ada Lovelace (RTX 4090) with FP8 KV cache and custom decode kernels. This repo targets NVF…☆155Feb 15, 2026Updated 8 months ago
- Qwen3.8-27B on one RTX 4090: full native 262K context via E8 4-bit KV, up to 149 tok/s code decode with MTP3, sm_89-retuned attention pre…☆223Updated this week
- TurboQuant llama.cpp fork with optimized turbo4 kernels for Gemma 4 D=256/512 heads — lazy K/V, batch decode, warp-cooperative write. 120…☆37Apr 5, 2026Updated 6 months ago
- One-click Qwen3.6-27B inference on Windows. 158 tok/s on RTX 5090, 72 tok/s on RTX 3090. Native, no WSL, no Docker, no telemetry.☆231May 14, 2026Updated 5 months ago
- LLM inference in C/C++☆35Oct 15, 2026Updated 2 weeks ago
- llama.cpp fork with TQ3_1S/4S CUDA kernels — 3.5-bit WHT quantization achieving Q4s quality at 10% smaller size. Based on RaBitQ-inspired…☆237Oct 13, 2026Updated 2 weeks ago
- llama.cpp fork for significantly improved performance on Ampere (especially RTX 3090 / 3090 Ti): example: 110+ tok/s over a 100K-token ge…☆207Updated this week
- LLM inference in C/C++☆12Oct 18, 2026Updated 2 weeks ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- A standalone, modular prompt generator for ComfyUI. Generate detailed, natural language prompts for characters and spaceships with extens…☆15Aug 3, 2026Updated 2 months ago
- turn qwen 3.6 27B-> AR -> diffusion (opendllm + d3llm)☆15Jun 11, 2026Updated 4 months ago
- Scripts to force Davinci Resolve to reload the latest version of media files☆14Jan 5, 2025Updated last year
- Durable local inference for Oh My Pi: NInfer + Qwen3.8 27B on one RTX 3090/4090/5090, with restart-resumable OpenAI Responses state.☆47Updated this week
- Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when …☆2,471Updated this week
- Custom sigma scheduler node for ComfyUI. Easily tune, visualize, and concatenate dynamic sigma curves with an interactive graph.☆12Sep 14, 2026Updated last month
- wav2lip-api☆11Mar 16, 2023Updated 3 years ago
- ☆31Aug 28, 2026Updated 2 months ago
- Локальная фотогалерея с AI-описанием, распознаванием лиц, кластеризацией персон и семантическим поиском.☆19Sep 5, 2026Updated last month
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Patched native-Windows build of vLLM. Three Windows-specific fixes (CPU-relay for Gloo, Qwen3 reasoning parser, wildcard model name) on t…☆28May 8, 2026Updated 5 months ago
- Merge your NAVER LINE chat history when you have an old database and a fresh install (Android - requires root).☆11Aug 31, 2023Updated 3 years ago
- Give your AI coding agent access to curated ML/AI knowledge.☆14Oct 5, 2026Updated 3 weeks ago
- Hyper optimised Qwen3.8-27B inference on one RTX 3090: ReplaySSM, MTP3, reasoning effort, C1-C8 batching, and native Windows and Linux bu…☆488Updated this week
- 自用的基于AI生成的chrome插件，官网api获取登录二维码，扫码后自动获取cookies信息，二维码令牌暂时还未调教好☆12Jul 12, 2025Updated last year
- A CUDA-accelerated GGUF quantization tool for NVFP4/MXFP6/Q_K, utilizing layer by layer quantization and selection techniques to reduce e…☆49Aug 15, 2026Updated 2 months ago
- Rex-Omni is a 3B-parameter Multimodal Large Language Model (MLLM) that redefines object detection and a wide range of other visual percep…☆12Oct 23, 2025Updated last year
- Experimental LLM inference in C/C++☆38May 15, 2026Updated 5 months ago
- Frida逆向实例和工具函数☆12Dec 31, 2025Updated 10 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- What I run on my inference server: Qwen3.8-Flash-Next on two RTX 3090s, and how I got here☆17Oct 12, 2026Updated 3 weeks ago
- ☆12Feb 19, 2025Updated last year
- Okta PKI Repository☆15Oct 6, 2026Updated 3 weeks ago
- Native Vulkan inference for giant MoE models on consumer AMD GPUs☆18Sep 22, 2026Updated last month
- Local-first persistent semantic memory and agent orchestration for Hermes, Claude Code, and MCP-compatible personal AI agents.☆15Updated this week
- Container driven LLM control for VLLM & llama models☆14Oct 20, 2026Updated last week
- Normalized Attention Guidance for ComfyUI Krea2.☆30Aug 11, 2026Updated 2 months ago