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.
☆233Oct 13, 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++☆2,431Updated this week
- Experimental llama.cpp fork for inference research and development☆887Updated this week
- KVarN, KV cache precision tail, low-bit quants in llama.cpp for longer context of better precision in the same VRAM☆1,166Updated this week
- Adaptive Precision for EXpert Models: MoE-aware mixed-precision quantization☆481Updated this week
- llama.cpp fork with TurboQuant WHT-rotated KV cache & weight compression + Gemma 4 MTP and Qwen 3.6 NextN speculative decoding (+30-50% t…☆423Oct 12, 2026Updated last week
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- LLM inference in C/C++☆57Updated this week
- Run the AEON Bench suite on your own hardware: verified HuggingFace pull → serve → benchmark (text · agentic ×3 harnesses · vision · audi…☆26Oct 6, 2026Updated 2 weeks ago
- llama.cpp fork with additional SOTA quants and improved performance☆3,310Updated this week
- LLM speculative inference server for heterogeneous hardware & consumer GPUs☆2,934Updated this week
- TurboQuant+ KV cache compression for vLLM. 3.8x smaller KV cache, same conversation quality. Fused CUDA kernels with automatic PyTorch fa…☆82Sep 19, 2026Updated last month
- Experimental LLM inference in C/C++☆39May 15, 2026Updated 5 months ago
- ☆68Jun 4, 2026Updated 4 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…☆1,054Apr 23, 2026Updated 5 months ago
- Structured Chain-of-Thought☆221May 16, 2026Updated 5 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.
- 1.0 Beta · oMLX 0.6.3rc2 Dual-ANE+CPU · Qwen3.8-27B abliterated oQ4e · Mac Studio M3 Ultra☆45Aug 23, 2026Updated last month
- An experimental and feature-rich inference engine built on top of llama.cpp☆81Updated this week
- TurboQuant KV cache compression for llama.cpp — HIP/ROCm port for AMD RDNA3 (gfx1100)☆54Apr 26, 2026Updated 5 months ago
- LLM inference in C/C++☆964Updated this week
- ☆16Jul 21, 2026Updated 2 months ago
- ROCmFPX Family for AMD Hardware and Processors. More quants and special agent quants☆417Sep 23, 2026Updated 3 weeks ago
- Autonomous self-improving 4x DGX Spark (GB10) MoA stack + LoRA loop (DSV4F router, Qwen3.6/Omni/TwoTower/Gemma). Hermes MoA routing, ~90%…☆24Aug 17, 2026Updated 2 months ago
- Qwen3.8-27B EXL3 (4.00 bpw) + DFlash2 speculative decoding for ExLlamaV3, validated at 262k context on a 24 GB RTX 3090☆25Sep 20, 2026Updated 3 weeks ago
- Deploy concurrent Hermes Agent workers on unified-memory GPUs (GB10, DGX Spark) for maximum total tok/s. Profile-isolated, kanban-coordin…☆83Jul 18, 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.
- Local benchmarking UI for LLMs and AI agents☆24Apr 13, 2026Updated 6 months ago
- VENDORIZED in lucebox-hub. Fork of llama.cpp, ggml graph for lucebox inference engine☆30Jul 8, 2026Updated 3 months ago
- [ICLR 2026] ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference☆345Aug 19, 2026Updated 2 months ago
- Tiny evaluation of leading LLMs on competitive programming problems☆14Apr 10, 2026Updated 6 months ago
- Qwen4-Exp (Qwen3.8-Flash-Next) SWA + MTP + PLE-on-iswa — bounded deep-context decode w/ long-range recall, TBQ4 4.25 bpv KV, DSpark + Rot…☆96Sep 24, 2026Updated 3 weeks ago
- Serve the official Ling-3.0-flash INT4 on one NVIDIA DGX Spark, 38.7 tok/s, faster than the community GGUF. Recipe, watchdog, benchmarks.☆26Aug 29, 2026Updated last month
- An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs☆1,703Updated this week
- A minimal MiniCPM5-1B model inference engine built purely in Rust☆42Aug 14, 2026Updated 2 months ago
- Control panel for VLLM, Sglang, llama.cpp, exllamav3☆1,830Oct 12, 2026Updated last 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.
- DFlash: Block Diffusion for Flash Speculative Decoding☆6,178Aug 18, 2026Updated 2 months ago
- ☆41Aug 16, 2026Updated 2 months ago
- Two agents spar over one codebase until every review finding is reconciled.☆27Jul 29, 2026Updated 2 months ago
- A self-evolving harness framework for Hermes Agent. Evolution + Critic + Verifier + Gardener cooperate to make your Hermes instance measu…☆61Jul 27, 2026Updated 2 months ago
- Unified KV-cache compression for LLM inference: 12 Python-native methods, guarded add-on composition and routing, analytical capacity sim…☆28Oct 10, 2026Updated last week
- Strata fork: Qwen3.8-Flash-Next 125B MoE in NVFP4 on one RTX 20-50 card (12 GB+) and 64 GB of RAM or more. Setup installs our GPTQ quants…☆170Updated 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 …☆2,108Updated this week