An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs
☆1,061Jul 21, 2026Updated this week
Alternatives and similar repositories for exllamav3
Users that are interested in exllamav3 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- The official API server for Exllama. OAI compatible, lightweight, and fast.☆1,283Updated this week
- ☆99Mar 28, 2026Updated 3 months ago
- A fast inference library for running LLMs locally on modern consumer-class GPUs☆4,590Mar 4, 2026Updated 4 months ago
- llama.cpp fork with additional SOTA quants and improved performance☆2,950Updated this week
- easy exllama interface w/ automation & evals☆17Updated this 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.
- Web UI for ExLlamaV2☆512Feb 5, 2025Updated last year
- Large-scale LLM inference engine☆1,808Updated this week
- ☆85Jun 20, 2025Updated last year
- ☆180Jun 22, 2025Updated last year
- REAP: Router-weighted Expert Activation Pruning for SMoE compression☆447Apr 17, 2026Updated 3 months ago
- Produce your own Dynamic 3.0 Quants and achieve optimum accuracy & SOTA quantization performance! Input a target size and the toolchain w…☆146Updated this week
- ik_llama.cpp's Thireus fork with release builds for macOS/Windows/Ubuntu CPU, Vulkan and CUDA☆165Updated this week
- Run GGUF models easily with a KoboldAI UI. One File. Zero Install.☆11,089Updated this week
- LLM model quantization (compression) toolkit with HW acceleration support for Nvidia, AMD, Intel GPU and Intel/AMD/Apple CPU via HF, vLLM…☆1,211Updated this week
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- A SOTA quantization algorithm for high-accuracy low-bit LLM inference, seamlessly optimized for CPU/XPU/CUDA, with multi-datatype support…☆1,533Updated this week
- Prompt Jinja2 templates for LLMs☆36Jul 9, 2025Updated last year
- Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc☆5,103Updated this week
- Fast LLM speculative inference server for consumer hardware.☆2,666Updated this week
- NVIDIA Linux open GPU with P2P support☆351Jul 13, 2026Updated last week
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆3,572Updated this week
- Auto-tuned launcher for GGUF models on llama.cpp / ik_llama.cpp — OpenAI-compatible server with multi-GPU tensor-split, MoE expert placem…☆256Updated this week
- A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.☆2,933Sep 30, 2023Updated 2 years ago
- ☆63Jul 10, 2025Updated last year
- 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.
- Croco.Cpp is fork of KoboldCPP infering GGML/GGUF models on CPU/Cuda with KoboldAI's UI. It's powered partly by IK_LLama.cpp, and compati…☆176Jul 3, 2026Updated 2 weeks ago
- KVarN, KV cache precision tail, low-bit quants in llama.cpp for longer context of better precision in the same VRAM☆797Updated this week
- Transplants vocabulary between language models, enabling the creation of draft models for speculative decoding WITHOUT retraining.☆54Oct 29, 2025Updated 8 months ago
- Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, llama.cpp, ik_llama) and model-agnostic. Currentl…☆1,771Updated this week
- [ICLR 2026] ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference☆326Jul 1, 2026Updated 3 weeks ago
- A high-throughput and memory-efficient inference and serving engine for LLMs (Windows build & kernels)☆577Jul 12, 2026Updated last week
- LLM Frontend in a single html file☆745Dec 27, 2025Updated 6 months ago
- A multimodal, function calling powered LLM webui.☆213Sep 23, 2024Updated last year
- ☆140Updated this 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.
- Test your local LLMs on the AIME problems☆39Jun 7, 2025Updated last year
- KV cache compression via block-diagonal rotation. Beats TurboQuant: better PPL (6.91 vs 7.07), 28% faster decode, 5.3x faster prefill, 44…☆1,038Apr 23, 2026Updated 3 months ago
- SNDR Core Engine (Genesis) — vLLM runtime patch-overlay for Qwen3.6 + Gemma4 on consumer NVIDIA (Ampere sm_86, 2× A5000/3090). Qwen3.6-35…☆125Updated this week
- Testbench for llama.cpp llama-server☆15Aug 20, 2025Updated 11 months ago
- SGLang is a high-performance serving framework for large language models and multimodal models.☆30,632Updated this week
- Work in progress.☆80Nov 25, 2025Updated 7 months ago
- Adaptive Precision for EXpert Models: MoE-aware mixed-precision quantization☆398May 29, 2026Updated last month