Convert and Run Exl3 format LLM quant on Apple Silicon.
☆58Aug 24, 2026Updated last month
Alternatives and similar repositories for PonyExl3
Users that are interested in PonyExl3 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Community registry of LLM serving-path traps that produce confidently wrong measurements: templates, tool parsers, reasoning fields, quan…☆135Updated this week
- Sushi engine runs very high quality quant model in Apple Silicon, using hybrid affine/exl3 with special expert tuning techniques.☆270Updated this week
- Minimal read-only OS image for GB10 (DGX Spark / ASUS GX10) boxes☆90Oct 4, 2026Updated last week
- A local inference engine for Apple silicon, built around the model.☆1,504Updated this week
- Low-latency collective transport and distributed LLM serving stack for switchless GB10 clusters.☆94Updated this week
- 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.
- Binary Ninja diffing tool☆97Oct 5, 2026Updated last week
- ☆41Jun 24, 2026Updated 3 months ago
- Silent Whisper inference for privacy and performance.☆13Oct 2, 2026Updated 2 weeks ago
- A server for streaming tweets by emulating browser Web Push.☆838Mar 5, 2026Updated 7 months ago
- Bounded TypeSafe Jev workflows for coding agents.☆117Sep 19, 2026Updated 3 weeks ago
- grep by meaning, across languages. TypeSafe Jev scores every line against a meaning; combine meanings with AND/OR/NOT. 意味で探す grep。日本語で英語を…☆150Updated this week
- Local agent infrastructure in one stdlib-only Go binary☆17Sep 7, 2026Updated last month
- A TUI (Terminal UI) dashboard for Github Spec-Kit☆92Sep 13, 2026Updated last month
- a community oriented 1:1, vLLM-alike (Continuous batching, paged KV) engine in C++ with additional features (GGUF, RadixAttention, Cache-…☆451Updated this week
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- A front door to community tools that extend the DeepSeek Harness (dsh): web access, vision, and more. Unofficial community project.☆42Sep 28, 2026Updated 2 weeks ago
- DeepSeek-V4-Flash-0731 284B inference in ~25 GB of RAM / Qwen3.8-Next-Flash inference in ~15 GB of RAM on any M-series MacBook☆143Updated this week
- Qwen3.8 Flash Next on one DGX Spark (TensorFold)☆263Updated this week
- Conformance and capability test suite for LLM inference engines — surface coverage, spec conformance, model capability, and an MTP/perfor…☆49Oct 5, 2026Updated last week
- Speak into the mic, and the character answers back in real time — with voice and video.☆62Updated this week
- Local inference engine for Qwen3.8-Flash-Next on NVIDIA Blackwell☆68Updated this week
- A knowledge-linked local AI harness with macOS support and a Windows Beta launcher.☆250Sep 14, 2026Updated last month
- Packer plugin for Lume☆16Updated this week
- Ad-free desktop music streaming application powered by YouTube.☆61Oct 9, 2026Updated last week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆40Updated this week
- Moved to nace-ai/drex-decision-models (archived)☆35Oct 9, 2026Updated last week
- ☆62Aug 4, 2026Updated 2 months ago
- The Finn-loop: a 3-skill AI software factory for Claude Code — spec, build, review. Humans merge.☆317Jul 23, 2026Updated 2 months ago
- a node-based graphic design tool☆136Aug 7, 2026Updated 2 months ago
- Use Jev to make art!☆63Sep 19, 2026Updated 3 weeks ago
- 解锁自有 NVIDIA CMP 170HX / 90HX 的算力限制。Linux x86-64，需要 root。☆57Aug 6, 2026Updated 2 months ago
- ☆128Jun 27, 2026Updated 3 months ago
- Run several Codex desktop accounts side by side, each with its own separate profile and login.☆46Oct 8, 2026Updated last week
- 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.
- DiffusionGemma NVFP4 structured decisions on a DGX Spark: container recipe☆220Sep 24, 2026Updated 3 weeks ago
- Metal Cuda Direct Memory Access☆196Updated this week
- ☆82Sep 18, 2026Updated 3 weeks ago
- 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…☆93Updated this week
- Complete and automated Gamebryo to TES5 plugin and asset conversion☆138Updated this week
- An always-listening voice AI assistant for a 32-bit ARM Android 11 (LineageOS 18.1) tablet.☆28Sep 17, 2026Updated last month
- Swift + Metal MoE inference for Apple Silicon: Qwen 3.6 35B at 23.5–29.3 tok/s decode with 2.20× faster long-prompt prefill on a 24 GB M5…☆122Sep 25, 2026Updated 3 weeks ago