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 ternary weights. Windows bundle + receipts.
☆100Nov 6, 2026Updated this week
Alternatives and similar repositories for bonsai-ada-surgery
Users that are interested in bonsai-ada-surgery are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 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 laye…☆109Updated this week
- ☆87Updated this week
- Ternary Bonsai 2 27B MLX inference speedup benchmark engine☆35Updated this week
- This project demonstrates the application of Hybrid Markov Logic Networks (MLN) to verify and refine embeddings from the Cora citation ne…☆16Apr 18, 2025Updated last year
- 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…☆172Oct 17, 2026Updated 3 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.
- PlayTrain: LLM-generated JavaScript game environments for RL☆12Oct 8, 2026Updated last month
- Official implementation of iSDFT: information-proximal on-policy self-distillation for continual learning in LLMs. Training code, checkpo…☆27Sep 22, 2026Updated last month
- Fast Opportunistic Mixture-Of-Experts. From-scratch C/HIP MoE inference with multi-tier caching and cache-aware routing. First ever examp…☆32Mar 31, 2026Updated 7 months ago
- Bigger local AI on the PC you already own. Find models, chat locally, and run supported sparse models across SSD, RAM and NVIDIA GPUs wit…☆22Updated this week
- LLM inference in C/C++☆1,006Updated this week
- マイナンバーカードの署名用電子証明書で、任意のファイルや PDF に電子署名を付与し、検証するデスクトップアプリケーション。☆24Nov 1, 2026Updated last week
- Qwen3.8-Flash-Next (125B MoE) on a 8GB+ Multi Vendor GPU 🥳No CUDA！☆331Oct 30, 2026Updated last week
- ☆58Oct 24, 2026Updated 2 weeks ago
- [NeurIPS 2025] MemEIC: A Step Toward Continual and Compositional Knowledge Editing☆24Mar 23, 2026Updated 7 months ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- A voice over network solution for WebRTC audio coming into and going out of Unreal Engine.☆10Jun 14, 2021Updated 5 years ago
- Dungeon Crawl Stone Soup port to iOS☆13Jan 7, 2025Updated last year
- A fully autonomous AI artist☆19Jun 19, 2023Updated 3 years ago
- Lane copy-on-write worktree strategy for OpenCode V2☆14Oct 14, 2026Updated 3 weeks ago
- Strata engine support for Gyro-M on 12 GB VRAM and 32 GB RAM☆16Oct 20, 2026Updated 2 weeks ago
- N64 Engine Powered by Libdragon☆13Apr 26, 2022Updated 4 years ago
- A STEP diff comment on every pull request: Specify's specify-core diff on build123d's cast bearing unit☆18Updated this week
- See what Hermes Agent left on your disk, inside Hermes Desktop: a treemap by what each folder is to Hermes, git-aware cards for what can …☆19Oct 23, 2026Updated 2 weeks 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
- 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.
- A full, unpruned 177B MoE model at 11.5 tok/s on one 12 GB GPU. Expert streaming for llama.cpp, with the measurement harness and every de…☆25Oct 3, 2026Updated last month
- Acoustic geolocation from the Doppler curves of propeller aircraft.☆197Updated this week
- 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…☆33Updated this week
- Cheap, isolated copy-on-write git worktrees for running many AI agents on one repo — an extra checkout costs metadata (~0.4 KiB per track…☆17Updated this week
- 📊 LLM Context Benchmarks - A comprehensive benchmarking tool for testing LLMs with varying context sizes using Ollama. Features dual b…☆106Oct 15, 2026Updated 3 weeks ago
- SVG-first slide generation toolkit with intelligent content planning and domain-specific layouts☆16Sep 8, 2026Updated 2 months ago
- GLM-5.3-Flash EXL3 on one 24 GB RTX 3090 + DDR4: elastic GPU expert cache, zero-copy experts, AVX2 CPU tier, OpenAI API☆349Oct 18, 2026Updated 3 weeks ago
- Microprice estimator for pretrade data☆14Nov 19, 2024Updated last year
- 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- …☆2,680Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Apple Calendar CLI for macOS — manage calendars and events from the command line☆13Oct 28, 2026Updated last week
- A small Node.js script that polls a website and sends a notification when there's a change. Inspired by my attempts to get a close hotel …☆13Nov 10, 2022Updated 3 years ago
- Fermion Research fork of llama.cpp: FV5/FV5B five-value ternary types for Neutrino GGUF packs (CPU + CUDA)☆14Sep 29, 2026Updated last month
- ☆11Aug 30, 2023Updated 3 years ago
- A GPSD simulator using a map☆11Feb 22, 2018Updated 8 years ago
- Home HQ: a family dashboard for a wall-mounted photo frame and phones. Rails 8, Hotwire, SQLite, Kamal.☆16Updated this week
- A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative…☆11Oct 13, 2026Updated 3 weeks ago