Adaptive Precision for EXpert Models: MoE-aware mixed-precision quantization
☆471Aug 17, 2026Updated last month
Alternatives and similar repositories for apex-quant
Users that are interested in apex-quant 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 fork with TQ3_1S/4S CUDA kernels — 3.5-bit WHT quantization achieving Q4s quality at 10% smaller size. Based on RaBitQ-inspired…☆229Updated this week
- llama.cpp fork with additional SOTA quants and improved performance☆3,244Updated this week
- KV cache compression via block-diagonal rotation. Beats TurboQuant: better PPL (6.91 vs 7.07), 28% faster decode, 5.3x faster prefill, 44…☆1,049Apr 23, 2026Updated 4 months ago
- LLM inference in C/C++☆2,386Updated this week
- Experimental llama.cpp fork for inference research and development☆866Updated this week
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- Produce your own Dynamic 3.0 Quants and achieve optimum accuracy & SOTA quantization performance! Input a target size and the toolchain w…☆166Sep 11, 2026Updated last week
- LLM speculative inference server for heterogeneous hardware & consumer GPUs☆2,868Updated this week
- KVarN, KV cache precision tail, low-bit quants in llama.cpp for longer context of better precision in the same VRAM☆1,096Sep 13, 2026Updated last week
- Fork of turbo quant tom-tom and TurboQuant KV cache from domwox☆31Jul 7, 2026Updated 2 months ago
- A pixel art space shooter built entirely by a 9B AI model on a single RTX 3060. Zero hand-written code.☆99Mar 19, 2026Updated 6 months ago
- 30 tok/s for 20B MoE on 8 GB VRAM. Flat throughput to 32K context. Native MXFP4 + GGUF Q4_K/Q5_K/Q6_K via ggml CUDA kernels — zero dequan…☆22Apr 7, 2026Updated 5 months ago
- Test LLMs on real tasks. Compare models side-by-side.☆421Aug 10, 2026Updated last month
- ☆32May 15, 2026Updated 4 months ago
- vLLM TurboQuant☆619Jun 25, 2026Updated 2 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.
- llama.cpp fork with TurboQuant WHT-rotated KV cache & weight compression + Gemma 4 MTP and Qwen 3.6 NextN speculative decoding (+30-50% t…☆411Sep 10, 2026Updated last week
- An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs☆1,459Updated this week
- REAP: Router-weighted Expert Activation Pruning for SMoE compression☆507Apr 17, 2026Updated 5 months ago
- ☆341May 15, 2026Updated 4 months ago
- Evolution process to find the best quant tensor weights to build the most optimal GGUF options for an AI model.☆46Sep 8, 2026Updated last 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…☆132Updated this week
- Gumbel-Softmax post-training quantization for LLMs (1–3 bit scalar, INT/GGUF-compatible).☆65Jul 11, 2026Updated 2 months ago
- LLM inference in C/C++☆64May 7, 2026Updated 4 months ago
- Structured Chain-of-Thought☆220May 16, 2026Updated 4 months ago
- 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.
- Distil SN97 — Competitive Model Distillation on Bittensor☆35May 20, 2026Updated 4 months ago
- ☆1,693Jul 11, 2026Updated 2 months ago
- Parakeet implementation in C++ with ggml☆786Aug 28, 2026Updated 3 weeks ago
- ☆20Jul 21, 2026Updated last month
- PolarEngine: vLLM plugin for PolarQuant quantized LLM inference — 75% FP16 speed at 2.3x less VRAM☆36Apr 13, 2026Updated 5 months ago
- ☆7,030Jul 20, 2026Updated 2 months ago
- ☆41Mar 31, 2026Updated 5 months ago
- pi.dev + llama.cpp ❤️☆25Jul 6, 2026Updated 2 months ago
- A harness optimized to smaller LLMs☆2,605Updated 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.
- Using LLMs for iteratively exploring the solution search space at scale.☆739Sep 5, 2026Updated 2 weeks ago
- DFlash block-diffusion speculative decoding running on Apple Silicon via MLX, with an ANE execution path that explores heterogeneous acce…☆61Apr 18, 2026Updated 5 months ago
- DFlash: Block Diffusion for Flash Speculative Decoding☆6,102Aug 18, 2026Updated last month
- Object-storage-native KV cache for LLM inference & RL. Cross-restart, cross-conversation, cross-engine via shared S3 bucket.☆19Aug 10, 2026Updated last month
- Using modal.com to process FineWeb-edu data☆21Sep 12, 2026Updated last week
- ☆397Apr 16, 2026Updated 5 months ago
- TurboQuant KV cache compression for llama.cpp — HIP/ROCm port for AMD RDNA3 (gfx1100)☆55Apr 26, 2026Updated 4 months ago