| | Gguf: Harden loader against malformed tensor dims and metadata types (github.com/ggml-org) |
| 3 points by gzxharrison001 24 days ago | past |
|
| | Release v0.2.0 · ggml-org/llama.cpp (github.com/ggml-org) |
| 4 points by kyisaiah47 25 days ago | past |
|
| | Llama-macOS – Agentic and MCP Native macOS Front End for Llama.cpp (github.com/ggml-org) |
| 6 points by car 33 days ago | past | 2 comments |
|
| | LLama.cpp Got Screwd (github.com/ggml-org) |
| 11 points by trilogic 72 days ago | past | 5 comments |
|
| | TurboPrefill: 2.7× faster than llama.cpp Pipeline Parallel on Llama-3-70B (github.com/ggml-org) |
| 3 points by trykhlieb 81 days ago | past |
|
| | Llama.cpp b9180: MTP support landed (github.com/ggml-org) |
| 2 points by usagisushi 4 months ago | past |
|
| | Grinder12: 0.96-Bit Lossless Streaming KV-Cache (16.55x VRAM Savings (github.com/ggml-org) |
| 3 points by AMICLLC 4 months ago | past |
|
| | Llama and Spec: MTP Support (github.com/ggml-org) |
| 1 point by jhoho 4 months ago | past |
|
| | Llama.cpp's Agents.md (github.com/ggml-org) |
| 4 points by Wowfunhappy 5 months ago | past | 1 comment |
|
| | Ggml.ai joins Hugging Face to ensure the long-term progress of Local AI (github.com/ggml-org) |
| 839 points by lairv 7 months ago | past | 223 comments |
|
| | Yet another reminder why you should not use Ollama (github.com/ggml-org) |
| 6 points by dcreater 7 months ago | past | 5 comments |
|
| | Show HN: Notebook page on llama.cpp official webui (github.com/ggml-org) |
| 1 point by hleszek 7 months ago | past |
|
| | LlamaBarn: A cosy home for your LLMs (github.com/ggml-org) |
| 2 points by tosh 7 months ago | past |
|
| | LlamaBarn – A macOS menu bar app for running local LLMs (github.com/ggml-org) |
| 3 points by lyapustin 10 months ago | past |
|
| | LlamaBarn – automatically configure models based on your Mac's hardware (github.com/ggml-org) |
| 2 points by smoser 10 months ago | past |
|
| | Llama.cpp launches official WebUI for local LLMs (github.com/ggml-org) |
| 4 points by victormustar 10 months ago | past |
|
| | Guide: Setting up Nvidia DGX Spark with ggml (github.com/ggml-org) |
| 2 points by homarp 11 months ago | past |
|
| | Llama.cpp: Deterministic Inference Mode (CUDA): RMSNorm, MatMul, Attention (github.com/ggml-org) |
| 6 points by diwank on Sept 15, 2025 | past |
|
| | A better Llama-CLI help doc (github.com/ggml-org) |
| 2 points by dcreater on Sept 2, 2025 | past | 1 comment |
|
| | Guide: Running GPT-OSS with Llama.cpp (github.com/ggml-org) |
| 2 points by homarp on Aug 21, 2025 | past |
|
| | Mistral Integration Improved in Llama.cpp (github.com/ggml-org) |
| 95 points by decide1000 on Aug 11, 2025 | past | 15 comments |
|
| | Llama.cpp: Add GPT-OSS (github.com/ggml-org) |
| 35 points by atgctg on Aug 5, 2025 | past |
|
| | AMD teams contributing to the llama.cpp codebase (github.com/ggml-org) |
| 3 points by gzer0 on July 28, 2025 | past |
|
| | Hunyuan-A13B model support has been merged into llama.cpp (github.com/ggml-org) |
| 2 points by empire23 on July 8, 2025 | past |
|
| | Whispercpp – Local, Fast, and Private Audio Transcription for Ruby (github.com/ggml-org) |
| 2 points by thunderbong on June 7, 2025 | past |
|
| | Vision Now Available in Llama.cpp (github.com/ggml-org) |
| 550 points by redman25 on May 10, 2025 | past | 104 comments |
|
| | Local LLM-assisted text completion extension for VS Code (github.com/ggml-org) |
| 3 points by raju on Jan 24, 2025 | past |
|
| | Llama.vim – Local LLM-assisted text completion (github.com/ggml-org) |
| 530 points by kgwgk on Jan 23, 2025 | past | 108 comments |
|
| | P1: LLM-based code completion engine at the edge (github.com/ggml-org) |
| 3 points by aduffy on June 20, 2023 | past |
|
