Hackernews posts about Llama 2

Llama 2 is a large language model AI designed to replace earlier models like GPT-3.5/4 and provide advanced natural language processing capabilities.

RSS feed for Llama 2

Related:Meta Qualcomm Cloudflare LeCun Vicuna

01
newShow HN: DOOM in the kernel, or fibers in eBPFayles.github.io
▲ 53ayles 26d 💬 14
02
newShow HN: PicoLM v1.0-rc2 ("Yura Kana"). Run an LLM on Digital Unixgithub.com
▲ 1gabucino 12d discuss
03
newFourier Analysis: Drawing Llamas with Circlesadekau.github.io
▲ 79cebert 12d 💬 11
04
newGetting 50 GB/S Back from the Apple Neural Engineeiln.github.io
▲ 218eiln 26d 💬 36
05
newLaunch HN: Magnitude (YC S25) – Self-optimizing inference engine for agentsgithub.com
▲ 194anerli 5d 💬 99
06
newLlama.cpp banned him for accidentally tagging in a fork PRgithub.com
▲ 1martianvoid 9d 💬 2
07
newShow HN: Llama.cpp fork with 2-4x multiGPU speed for MoE models bigger than VRAMgithub.com
▲ 2neuralll 10d 💬 3
08
newI got 2.2x more tokens per second from llama.cpp on Intel Arcgrigio.org
▲ 4grigio 8d discuss
09
newSSD-Llama: SSD-Native Inference for Trillion-Parameter Moe on a Consumer PCarxiv.org
▲ 3AlmostCosmo79 17d discuss
10
newOpen-Source E2E FHE Implementation for Privacy-Preserving Llama 3 8B Inferencearxiv.org
▲ 2simonpure 8d discuss
11
newShow HN: IttyBittyAI – Qwen2.5:0.5B running on a 2017 Asus smartphone
▲ 2spottedmarley 11d discuss
12
newWhy human syntax breaks LLMs (and how to fix agentic coding)
▲ 5aslang 28d 💬 3
13
newShow HN: Nibia Fabric – Turn everyday computers into a shared AI compute clustergithub.com
▲ 1abelop 7d 💬 3
14
newShow HN: Prodigy – The Self-Updating Technical Digestwww.prodigy.org.in
▲ 1samayashar 9d discuss
15
newOllama replacement 2-4x faster for no extra compute costgithub.com
▲ 4wowitsbase 28d 💬 4
16
newShow HN: Ollama stand in replacement, 2-4x faster, not just basic optimizationsgithub.com
▲ 3wowitsbase 27d discuss
17
newShow HN: Breadcrumb, record everything on your mac + context manager for AIinnerloop.works
▲ 49jv22222 4d 💬 9
18
newShodan indexes over 47.000 exposed Ollama instancestwitter.com
▲ 2soltanov 19d 💬 1
19
newShow HN: Pizza Bot – An inbox for AI agents that work in the backgroundgithub.com
▲ 61jd_20d 💬 37
20
newShow HN: I compiled FreeRDP into a Flutter app so my phone can do RDP and SSHxconnectapp.com
▲ 4neil_thomas 17d discuss
21
newShow HN: Yengi, a local-first AIdevelopment environment for coding,Blender/Unitygithub.com
▲ 2mdaiWorks 7d discuss
22
newShow HN: Blackbear.app – Thoughtful, Private Collaborationblackbear.app
▲ 2rheisen_11d discuss
23
newShow HN: Echodot – Local-first AI that writes replies in your tonegithub.com
▲ 2kariku 19d discuss
24
newShow HN: A Coding Agent from Scratchblog.softwarewrighter.com
▲ 2softwarewright 19d discuss
25
newShow HN: I made a tiny MoE/Engram viz toolsw-ml-study.github.io
▲ 2softwarewright 22d discuss
26
newShow HN: MaskShift – a maximalist coding agent with zero NPM dependenciesgithub.com
▲ 1Nafeeur 29d discuss
27
newFruit of the Poisonous Llama? (2023)shkspr.mobi
▲ 32edent 606d 💬 41
28
newA complete Llama2 inference engine that fits in 1356 bytes of x86 assemblygithub.com
▲ 27monax 154d discuss
29
newLlama 2 LLM on DOSyeokhengmeng.com
▲ 11ingve 538d discuss
30
newShow HN: Llama2.c on a Commodore C64github.com
▲ 10AMICABoard 590d 💬 7
31
newLlama 2 inference from scratch in C++20 (No PyTorch/GGML, ARM NEON)github.com
▲ 8recoverydial 272d discuss
32
newLlama2.c64: a port of llama2.c to the Commodore C64github.com
▲ 8adunk 523d discuss
33
newL2E llama2.c running in a PDF in a Shroedinger PNG [pdf]github.com
▲ 6AMICABoard 628d 💬 2
34
newLlama2.c Running in a PDFgithub.com
▲ 6AMICABoard 628d 💬 1
35
newllama2.zig: Inference Llama 2 in one file of pure Ziggithub.com
▲ 5tosh 304d discuss
36
newMeta's Llama 2 license is not Open Sourceopensource.org
▲ 4pauloxnet 612d 💬 1
37
newLlama2.c LLM on Vintage Sega Dreamcast Clustertwitter.com
▲ 4AMICABoard 623d 💬 1
38
newL2E llama2.c is running on those ancient-ass Amigastwitter.com
▲ 3AMICABoard 623d 💬 1
39
newThe Winamp Skin Museum whips the Llama's ass (2020)www.rockpapershotgun.com
▲ 3Michelangelo11 124d discuss
40
newBare-Metal Llama 2 Inference in C++20 (No Frameworks, ARM Neon)github.com
▲ 3ornurla 271d discuss
41
newL2E Llama2.c in a PDF in a ZIP in a PNG in a X post / tweettwitter.com
▲ 3AMICABoard 627d discuss
42
newHelp needed to improve Haskell port of Andrej Karpathy's llama2.cgithub.com
▲ 3CertumIter 708d discuss
43
newShow HN: A book that builds GPT-2, Llama 3, DeepSeek from scratch in PyTorch
▲ 2s1lv3rj1nx 173d 💬 1
44
newModern AI on Vintage Hardware: Llama 2 Runs on Windows 98hackaday.com
▲ 2JumpCrisscross 349d 💬 1
45
newLlama 2 LLM on DOS (2025)yeokhengmeng.com
▲ 2userbinator 89d discuss
46
newLlama2.c on the Commodore C64github.com
▲ 2radeeyate 519d discuss
47
newLlama 2 LLM on DOSyeokhengmeng.com
▲ 2ingve 537d discuss
48
newLlama 2 LLM on DOSyeokhengmeng.com
▲ 2ingve 538d discuss
49
newLlama2.c (early alpha) on Sharp X68030twitter.com
▲ 2AMICABoard 617d discuss
50
newllama2psp: llama2.c running on the PSPgithub.com
▲ 2pizza 677d discuss
51
newCan You Run the Llama 2 LLM on DOS?yeokhengmeng.com
▲ 1based2 532d 💬 1
52
newShow HN: L2E Llama2.c in a PDF in a Polyglot PNGtwitter.com
▲ 1AMICABoard 628d 💬 1
53
newSagence emerges from stealth promising Llama 2 at 10 percent powerspectrum.ieee.org
▲ 1pseudolus 685d discuss
54
newShow HN: Open Computer Usegithub.com
▲ 9mlejva 620d 💬 1
55
newShow HN: I built a programming language, inspired by Golanggithub.com
▲ 7weiwenhao 504d 💬 2
56
newAsk HN: How are you managing LLM inference at the edge?
▲ 7gray_amps 515d 💬 2