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 Walsh-Hadamard transform. Enables 27B models on 16GB GPUs with 15 tok/s TG, 221 tok/s PP.
☆228Aug 18, 2026Updated this week
Alternatives and similar repositories for llama.cpp-tq3
Users that are interested in llama.cpp-tq3 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- LLM inference in C/C++☆2,291Updated this week
- Experimental llama.cpp fork for inference research and development☆759Updated this week
- KVarN, KV cache precision tail, low-bit quants in llama.cpp for longer context of better precision in the same VRAM☆886Updated this week
- Run the AEON Bench suite on your own hardware: verified HuggingFace pull → serve → benchmark (text · agentic ×3 harnesses · vision · audi…☆23Updated this week
- Adaptive Precision for EXpert Models: MoE-aware mixed-precision quantization☆440Updated this week
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- llama.cpp fork with TurboQuant WHT-rotated KV cache & weight compression + Gemma 4 MTP and Qwen 3.6 NextN speculative decoding (+30-50% t…☆353Aug 6, 2026Updated last week
- LLM inference in C/C++☆56Updated this week
- LLM speculative inference server for consumer & heterogeneous hardware☆2,762Updated this week
- llama.cpp fork with additional SOTA quants and improved performance☆3,056Updated this week
- TurboQuant+ KV cache compression for vLLM. 3.8x smaller KV cache, same conversation quality. Fused CUDA kernels with automatic PyTorch fa…☆79Jul 14, 2026Updated last month
- Experimental LLM inference in C/C++☆40May 15, 2026Updated 3 months ago
- Structured Chain-of-Thought☆219May 16, 2026Updated 3 months ago
- KV cache compression via block-diagonal rotation. Beats TurboQuant: better PPL (6.91 vs 7.07), 28% faster decode, 5.3x faster prefill, 44…☆1,045Apr 23, 2026Updated 3 months ago
- PolarEngine: vLLM plugin for PolarQuant quantized LLM inference — 75% FP16 speed at 2.3x less VRAM☆34Apr 13, 2026Updated 4 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- LLM inference in C/C++☆64May 7, 2026Updated 3 months ago
- ROCmFPX Family for AMD Hardware and Processors. More quants and special agent quants☆262Updated this week
- TurboQuant KV cache compression for llama.cpp — HIP/ROCm port for AMD RDNA3 (gfx1100)☆56Apr 26, 2026Updated 3 months ago
- Deploy concurrent Hermes Agent workers on unified-memory GPUs (GB10, DGX Spark) for maximum total tok/s. Profile-isolated, kanban-coordin…☆79Jul 18, 2026Updated last month
- ☆7,004Jul 20, 2026Updated 3 weeks ago
- Local benchmarking UI for LLMs and AI agents☆23Apr 13, 2026Updated 4 months ago
- [ICLR 2026] ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference☆328Jul 1, 2026Updated last month
- EOQ: Entropy-Optimal Quantization for LLMs. 11-41% smaller than GGUF Q4_K_M with near-FP16 perplexity.☆46Updated this week
- Fused TBQ4 Flash Attention + MTP + Shared Tensors for llama.cpp — 82+ tok/s with lossless 4.25 bpv KV cache at 200K context on RTX 4090☆90Updated this week
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- DFlash: Block Diffusion for Flash Speculative Decoding☆5,643May 10, 2026Updated 3 months ago
- Fully uncensored, capability-enhanced abliteration of Qwen3.6-27B. NVFP4 + z-lab DFlash speculative decoding (n=12) on the unified ghcr.i…☆445Jul 3, 2026Updated last month
- Distil SN97 — Competitive Model Distillation on Bittensor☆35May 20, 2026Updated 2 months ago
- Test LLMs on real tasks. Compare models side-by-side.☆408Aug 10, 2026Updated last week
- Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, llama.cpp, ik_llama) and model-agnostic. Currentl…☆2,010Updated this week
- ☆24May 30, 2026Updated 2 months ago
- A CLI tool that automates the provisioning of GPU's across cloud providers and the running of AI experiments across them☆23Jun 1, 2026Updated 2 months ago
- Reproducible llama.cpp configs + per-category quality benches for Qwen3.6-27B on a single RTX 4090. Winners, dead ends, and the silent-co…☆23Apr 26, 2026Updated 3 months ago
- Code for the paper *Attention Drift: What Speculative Decoding Models Learn*.☆28May 12, 2026Updated 3 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- High-fidelity ASCII art pipeline — edge-aware downsampling, video eikons, Risomorphism 1911 aesthetic☆30May 15, 2026Updated 3 months ago
- Universal REPL Bridge for LLMs - Tab completion, interactive prompts, TUI support☆20Nov 24, 2025Updated 8 months ago
- TriAttention — Efficient long reasoning with trigonometric KV cache compression. Enables OpenClaw local deployment on memory-constrained …☆842Aug 4, 2026Updated 2 weeks ago
- LLM inference in C/C++☆460Updated this week
- An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs☆1,141Updated this week
- NEW ROCmfp4 format for llama.cpp☆146Jun 13, 2026Updated 2 months ago
- ☆10Oct 24, 2024Updated last year