Mirai S (Qwen3.8-27B-S trellis GGUF) on a 12 GB RTX 4070: 262k q8_0 tiered cache, MTP drafting at every depth, harness-proofing, the layer; receipts.
☆109Oct 26, 2026Updated last week
Alternatives and similar repositories for mirai-s-ada
Users that are interested in mirai-s-ada are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- llama.cpp with Mirai S (2.4-bit Qwen3.8-27B) support: 128K context on a 12 GB GPU☆11Oct 7, 2026Updated 3 weeks ago
- Bonsai 2 27B: 262k context (trained max) on 12 GB, 54 to 97 tok/s decode, 2x prefill, q8_0 KV recipe, grammar tool calls 9/9. Same ternar…☆100Updated this week
- ☆30Updated this week
- Qwen3.8-Flash-Next (125B MoE) on a 8GB+ Multi Vendor GPU 🥳No CUDA！☆321Oct 30, 2026Updated last week
- Qwen3.8-27B on 16-32 GB Nvidia GPUs one-click install for Windows / Linux☆600Oct 9, 2026Updated 3 weeks ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- run a 27b local ai on your gaming gpu, rtx 3060 and up, radeon rx 6600 and up in beta, 8gb or more, linux and windows, one line to instal…☆171Oct 17, 2026Updated 2 weeks ago
- Open-source AI old photo restoration tool — production-ready Next.js SaaS that colorizes, denoises, and repairs damaged vintage photos. F…☆15Jul 27, 2026Updated 3 months ago
- The agent that grows with you☆14Oct 14, 2026Updated 3 weeks ago
- One-menu RTX 5090 installer for the abliterated Qwen3.8-Flash-Next on fngine: pinned build with isolated CUDA, verified download, serving…☆14Oct 15, 2026Updated 3 weeks ago
- Bend's landing page☆18Sep 9, 2026Updated last month
- Run GLM-5.3-Flash (321B), DeepSeek-V4.1-Flash (748B) and MiniMax-M3.1-Flash (428B) on your own GPUs - one engine, one dashboard, OpenAI- …☆2,585Updated this week
- Deployment kit: Qwen3.8-27B EXL3 3.5bpw target + DFlash2 EXL3 5.0bpw speculative draft — launcher, config, model cards☆233Sep 1, 2026Updated 2 months ago
- LINEAE: An enhanced version of high-speed, high-precision line detection using Scalable Transformers. Built with DINOv3.☆36Aug 2, 2026Updated 3 months ago
- LLM Inference Engine for Metal, CUDA and Vulkan.☆1,677Updated this week
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- LLM serving engines that SkyDiscover builds on the fly for specific AI models and hardware: Qwen3.6-35B-A3B, Qwen3.8-Flash-Next and Flint…☆26Updated this week
- Strata fork that runs GLM-5.3-Flash (320B-A18B, 157 GB) on one PC: RTX 5090 + 128 GB RAM + NVMe, ~30 tok/s chat. Fork of Niko1221/Strata …☆37Oct 13, 2026Updated 3 weeks ago
- Open quantization tooling for TurboQuant-style low-bit LLM releases, stock GGUF deployment, and Apple Silicon runtime experiments.☆10May 5, 2026Updated 6 months ago
- KVarN, KV cache precision tail, low-bit quants in llama.cpp for longer context of better precision in the same VRAM☆1,183Updated this week
- VS Code extension that turns your TODO.md into an interactive Kanban board and runs autonomous Claude Code agent loops per task — markdow…☆19Updated this week
- Drive Kernel cloud browsers from bb ide — CLI commands, native agent tools, and a live browser view in your bb threads.☆17Sep 3, 2026Updated 2 months ago
- One click installer for 8GB gpus + Integration with StableProjectorz☆16Apr 22, 2026Updated 6 months ago
- One llama.cpp flag unlocks +33-39% decode speed for Qwen3.8-27B on consumer GPUs. The MTP head already ships inside your GGUF. Recipe, pa…☆367Sep 26, 2026Updated last month
- llama.cpp fork that abliterates at inference☆166Oct 24, 2026Updated 2 weeks ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- 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 …☆2,580Updated this week
- What actually runs on an RTX 3060 12GB, if you have any card with 12GB vram, this is for you as well. measured, with commands☆163Aug 22, 2026Updated 2 months ago
- LLM inference in C/C++☆24Oct 21, 2026Updated 2 weeks ago
- GPGPU array on Vulkan☆17Jun 3, 2023Updated 3 years ago
- Truthful scheduler-step and streaming visualization for local LLM inference☆35Sep 6, 2026Updated 2 months ago
- ☆17Sep 16, 2026Updated last month
- ☆52Updated this week
- Portable company harness methods, DeepSeek Harness presets, and AI-native operating artifacts.☆32Aug 18, 2026Updated 2 months ago
- ☆35Updated this week
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- One-menu RTX 5090 installer for fafstmobel with Cinference, DFlash2, K8V4, and vision.☆25Oct 2, 2026Updated last month
- Strata-based GLM 5.3 Flash runner☆19Updated this week
- ush is modern sh☆17Sep 5, 2026Updated 2 months ago
- Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on loca…☆40,925Updated this week
- DeepSeek 4 Flash local inference engine for Metal and CUDA with M5 optimizations.☆25May 24, 2026Updated 5 months ago
- ☆22Oct 18, 2026Updated 2 weeks ago
- Reason over explicit states, many branches at once: merge duplicates, cancel dead ends, advance together.☆181Oct 3, 2026Updated last month