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.
☆230Sep 26, 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++☆2,406Updated this week
- Experimental llama.cpp fork for inference research and development☆875Updated this week
- KVarN, KV cache precision tail, low-bit quants in llama.cpp for longer context of better precision in the same VRAM☆1,126Updated this week
- Adaptive Precision for EXpert Models: MoE-aware mixed-precision quantization☆475Aug 17, 2026Updated last month
- llama.cpp fork with TurboQuant WHT-rotated KV cache & weight compression + Gemma 4 MTP and Qwen 3.6 NextN speculative decoding (+30-50% t…☆416Sep 22, 2026Updated last 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.
- LLM inference in C/C++☆56Updated this week
- LLM speculative inference server for heterogeneous hardware & consumer GPUs☆2,883Updated this week
- llama.cpp fork with additional SOTA quants and improved performance☆3,260Updated this week
- ☆68Jun 4, 2026Updated 3 months ago
- Experimental LLM inference in C/C++☆40May 15, 2026Updated 4 months ago
- Structured Chain-of-Thought☆220May 16, 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…☆1,049Apr 23, 2026Updated 5 months ago
- LLM inference in C/C++☆64May 7, 2026Updated 4 months ago
- Deploy concurrent Hermes Agent workers on unified-memory GPUs (GB10, DGX Spark) for maximum total tok/s. Profile-isolated, kanban-coordin…☆81Jul 18, 2026Updated 2 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- ROCmFPX Family for AMD Hardware and Processors. More quants and special agent quants☆404Updated this week
- VENDORIZED in lucebox-hub. Fork of llama.cpp, ggml graph for lucebox inference engine☆30Jul 8, 2026Updated 2 months ago
- ☆7,035Jul 20, 2026Updated 2 months ago
- Local benchmarking UI for LLMs and AI agents☆24Apr 13, 2026Updated 5 months ago
- [ICLR 2026] ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference☆341Aug 19, 2026Updated last month
- EOQ: Entropy-Optimal Quantization for LLMs. 11-41% smaller than GGUF Q4_K_M with near-FP16 perplexity.☆46Sep 4, 2026Updated 3 weeks 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…☆95Updated this week
- Control panel for VLLM, Sglang, llama.cpp, exllamav3☆1,804Updated this week
- DFlash: Block Diffusion for Flash Speculative Decoding☆6,123Aug 18, 2026Updated last month
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Fully uncensored, capability-enhanced abliteration of Qwen3.6-27B. NVFP4 + z-lab DFlash speculative decoding (n=12) on the unified ghcr.i…☆468Sep 15, 2026Updated 2 weeks ago
- Unified KV-cache compression for LLM inference: 12 Python-native methods, guarded add-on composition and routing, analytical capacity sim…☆26Aug 22, 2026Updated last month
- Distil SN97 — Competitive Model Distillation on Bittensor☆35May 20, 2026Updated 4 months ago
- ☆25Sep 3, 2026Updated 3 weeks 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…☆24Apr 26, 2026Updated 5 months ago
- Gumbel-Softmax post-training quantization for LLMs (1–3 bit scalar, INT/GGUF-compatible).☆74Jul 11, 2026Updated 2 months ago
- An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs☆1,530Updated this week
- Code for the paper *Attention Drift: What Speculative Decoding Models Learn*.☆28May 12, 2026Updated 4 months ago
- High-fidelity ASCII art pipeline — edge-aware downsampling, video eikons, Risomorphism 1911 aesthetic☆30Updated 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.
- Universal REPL Bridge for LLMs - Tab completion, interactive prompts, TUI support☆20Nov 24, 2025Updated 10 months ago
- TriAttention — Efficient long reasoning with trigonometric KV cache compression. Enables OpenClaw local deployment on memory-constrained …☆852Aug 4, 2026Updated last month
- DGX Spark / GB10 vLLM image for Gemma 4 31B Deckard Heretic Uncensored NVFP4 with z-lab DFlash speculative decoding.☆34May 15, 2026Updated 4 months ago
- LLM inference in C/C++☆803Updated this week
- NEW ROCmfp4 format for llama.cpp☆157Jun 13, 2026Updated 3 months ago
- ☆10Oct 24, 2024Updated last year
- ☆46Feb 20, 2026Updated 7 months ago