An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs
☆1,772Oct 31, 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.☆1,502Updated this week
- A fast inference library for running LLMs locally on modern consumer-class GPUs☆4,648Mar 4, 2026Updated 7 months ago
- llama.cpp fork with additional SOTA quants and improved performance☆3,354Updated this week
- ☆100Mar 28, 2026Updated 7 months ago
- ☆198Jun 22, 2025Updated last year
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Large-scale LLM inference engine☆1,899Updated this week
- KVarN, KV cache precision tail, low-bit quants in llama.cpp for longer context of better precision in the same VRAM☆1,177Updated this week
- easy exllama interface w/ automation & evals☆19Sep 25, 2026Updated last month
- Web UI for ExLlamaV2☆517Feb 5, 2025Updated last year
- LLM speculative inference server for heterogeneous hardware & consumer GPUs☆2,967Updated this week
- Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc☆6,144Updated this week
- ☆97Jun 20, 2025Updated last year
- REAP: Router-weighted Expert Activation Pruning for SMoE compression☆536Apr 17, 2026Updated 6 months ago
- Unlock P2P comms between consumer NVIDIA GPUs☆684Updated 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.
- PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率，量化感知训练的精度☆1,697Updated this week
- Produce your own Dynamic 3.0 Quants and achieve optimum accuracy & SOTA quantization performance! Input a target size and the toolchain w…☆171Sep 11, 2026Updated last month
- Deployment kit: Qwen3.8-27B EXL3 3.5bpw target + DFlash2 EXL3 5.0bpw speculative draft — launcher, config, model cards☆233Sep 1, 2026Updated last month
- a community oriented 1:1, vLLM-alike (Continuous batching, paged KV) engine in C++ with additional features (GGUF, RadixAttention, Cache-…☆474Updated this week
- Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on loca…☆36,894Updated this week
- KoboldCpp - Run GGUF AI models locally with a KoboldAI UI. One File. Zero Install.☆12,111Updated this week
- High-performance single-GPU inference for selected model checkpoints and GPUs.☆3,223Updated this week
- LLM Inference Engine for Metal, CUDA and Vulkan.☆1,559Updated this week
- an experimental quantized training library☆15Updated 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.
- Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, sglang, llama.cpp and other custom engines) and m…☆2,466Updated 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 …☆2,456Updated this week
- Project Maya - run GLM-5.3-Flash (321B MoE), DeepSeek-V4.1-Flash-1017 (748B MoE) and MiniMax-M3.1-Flash (428B MoE) privately on your own …☆2,317Updated this week
- llama.cpp/ik_llama.cpp launcher: loads big MoE models across mismatched multi-GPU rigs by exact VRAM math.☆282Updated this week
- FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.☆14,868Updated this week
- SNDR Core Engine (Genesis) — vLLM runtime patch-overlay for Qwen3.6 + Gemma4 on consumer NVIDIA (Ampere sm_86, 2× A5000/3090). Qwen3.6-35…☆133Sep 30, 2026Updated last month
- State-of-the-art LLM compression, built for production inference with vLLM☆3,931Updated this week
- 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…☆184Sep 18, 2026Updated last month
- LLM model quantization (compression) toolkit with HW acceleration support for Nvidia, AMD, Intel GPU and Intel/AMD/Apple CPU via HF, vLLM…☆1,283Updated 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.
- A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.☆2,944Sep 30, 2023Updated 3 years ago
- Archived: b12x development has moved to FlashInfer. See README for migration and PR-porting guidance.☆268Oct 6, 2026Updated 3 weeks ago
- Control panel for VLLM, Sglang, llama.cpp, exllamav3☆1,836Updated this week
- Experimental llama.cpp fork for inference research and development☆896Updated this week
- DFlash: Block Diffusion for Flash Speculative Decoding☆6,209Aug 18, 2026Updated 2 months ago
- LLM inference in C/C++☆132,963Updated this week
- Adaptive Precision for EXpert Models: MoE-aware mixed-precision quantization☆482Oct 14, 2026Updated 2 weeks ago