Smart News

Hackernews posts about Llama.cpp

RSS feed for Llama.cpp
Related:M2 Max
  1. 01
    Llama.cpp on a jailbroken PS5: run any GGUF model natively on the consolegithub.com
    ▲ 161Anon845h💬 45
  2. 02
    Faster prompt lookup drafting in llama.cppjadidbourbaki.github.io
    ▲ 89pptadversary20d💬 12
  3. 03
    New in Llama.cpp: Decision Modelshuggingface.co
    ▲ 6cuvinny14d💬 1
  4. 04
    SonicBoom – llama.cpp's own kernels, 14% faster decode via a graph compilergithub.com
    ▲ 4nalaginrut3ddiscuss
  5. 05
    Llama.cpp and WebGPU = Client-side LLMs [video]www.youtube.com
    ▲ 4TriteJin9ddiscuss
  6. 06
    I got 2.2x more tokens per second from llama.cpp on Intel Arcgrigio.org
    ▲ 4grigio18ddiscuss
  7. 07
    Llama.cpp Under the Hoodwww.cppdepend.com
    ▲ 4cppfirst23ddiscuss
  8. 08
    Transformers now runs llama.cpp quantshuggingface.co
    ▲ 4mmis100023ddiscuss
  9. 09
    Benchmarking Local LLM Servers: Llama.cpp, Llamafile, LM Studio, and Ollamablog.mozilla.ai
    ▲ 3angpt29d💬 2
  10. 10
    Jeyzma is TypeSafeAI minus $850M plus Go/TinyGo/llama.cpp in the browserjeyzma.com
    ▲ 3deadprogram6ddiscuss
  11. 11
    AI Development on Windows: From PyTorch and Llama.cpp to Windows MLdevblogs.microsoft.com
    ▲ 3antimora9ddiscuss
  12. 12
    New in Llama.cpp: Decision Modelshuggingface.co
    ▲ 3nreece13ddiscuss
  13. 13
    Show HN: Jeva.cpp – a llama.cpp fork with JEV-compatible API for all LLMsgithub.com
    ▲ 3pragmatwice18ddiscuss
  14. 14
    Show HN: Llama.cpp fork with 2-4x multiGPU speed for MoE models bigger than VRAMgithub.com
    ▲ 2neuralll21d💬 3
  15. 15
    PS5LM: Llama.cpp on a jailbroken PS5, run any GGUF model natively on the consolegithub.com
    ▲ 2zdw2ddiscuss
  16. 16
    MS announces DeepSeek V4 Flash and Nemotron locally, llama.cpp comes to Win MLpasqualepillitteri.it
    ▲ 2choult9ddiscuss
  17. 17
    Custom Models in Oh My Pi: vLLM, Llama.cpp, SGLang and Moredoug.sh
    ▲ 2dougcalobrisi20ddiscuss
  18. 18
    Transformers now runs llama.cpp quantshuggingface.co
    ▲ 2vertigoruntime24ddiscuss
  19. 19
    Llama.cpp banned him for accidentally tagging in a fork PRgithub.com
    ▲ 1martianvoid19d💬 2
  20. 20
    If llama.cpp enables MoE to activate multiple expertswww.openai-hub.com
    ▲ 1ConteMascetti7126hdiscuss
  21. 21
    AI Development on Windows: From PyTorch and Llama.cpp to Windows MLdevblogs.microsoft.com
    ▲ 1pjmlp8ddiscuss
  22. 22
    Show HN: Reflex Engine Beats Both Llama.cpp and vLLM on Cold-Start to TTFTgithub.com
    ▲ 1leochong16ddiscuss
  23. 23
    ContextMemory – Markdown memory for your llama.cpp/vLLM servergithub.com
    ▲ 1vitorcastro7817ddiscuss
  24. 24
    Launch HN: Magnitude (YC S25) – Self-optimizing inference engine for agentsgithub.com
    ▲ 194anerli16d💬 97
  25. 25
    Show HN: IttyBittyAI – Qwen2.5:0.5B running on a 2017 Asus smartphone
    ▲ 2spottedmarley22ddiscuss
  26. 26
    Show HN: Nibia Fabric – Turn everyday computers into a shared AI compute clustergithub.com
    ▲ 1abelop18d💬 3
  27. 27
    Show HN: LoRA over GGUF – Train Qwen3.8-Flash-Next in 40G VRAMgithub.com
    ▲ 1woctordho6ddiscuss
  28. 28
    Show HN: Long term memory agent for "real world" data workgithub.com
    ▲ 1jad19089ddiscuss
  29. 29
    Vision Now Available in Llama.cppgithub.com
    ▲ 550redman25524d💬 104
  30. 30
    Llama.cpp guide – Running LLMs locally on any hardware, from scratchsteelph0enix.github.io
    ▲ 368zarekr686d💬 87
  31. 31
    llama.cppllama.app
    ▲ 364kristianpaul65d💬 164
  32. 32
    Apple Silicon and macOS VMs: Faster LLM Inference with llama.cppgithub.com
    ▲ 307frabonacci66d💬 41
  33. 33
    Heap-overflowing Llama.cpp to RCEretr0.blog
    ▲ 248retr0reg572d💬 54
  34. 34
    Llama.cpp supports Vulkan. why doesn't Ollama?github.com
    ▲ 217buyucu623d💬 228
  35. 35
    Ollama violating llama.cpp license for over a yeargithub.com
    ▲ 202Jabrov518d💬 68
  36. 36
    Llama.cpp Now Supports Qwen2-VL (Vision Language Model)github.com
    ▲ 155BUFU671d💬 50
  37. 37
    Go library for in-process vector search and embeddings with llama.cppgithub.com
    ▲ 114kelindar718d💬 29
  38. 38
    Llama.cpp AI Performance with the GeForce RTX 5090 Reviewwww.phoronix.com
    ▲ 113kristianp585d💬 78
  39. 39
    Mistral Integration Improved in Llama.cppgithub.com
    ▲ 95decide1000431d💬 15
  40. 40
    Georgi Gerganov on llama.cpp/ggml future after Nvidia acquisition of HuggingFacetwitter.com
    ▲ 76theanonymousone42d💬 28
  41. 41
    Llama.cpp: Add GPT-OSSgithub.com
    ▲ 35atgctg437ddiscuss
  42. 42
    Building a Rust Inference Engine That Matches Llama.cppwww.fratepietro.com
    ▲ 23antonellof72d💬 41
  43. 43
    Llama.cpp now has an official website: llama.apptwitter.com
    ▲ 17julien_c140d💬 4
  44. 44
    Show HN: Llama.cpp Tutorial 2026: Run GGUF Models Locally on CPU and GPU
    ▲ 13anju-kushwaha181d💬 4
  45. 45
    Show HN: Minute – Offline meeting notes on macOS with Whisper and llama.cppgithub.com
    ▲ 12mraza00780d💬 6
  46. 46
    LLama.cpp Got Screwdgithub.com
    ▲ 11trilogic99d💬 5
  47. 47
    Ask HN: Is anybody using llama.cpp for production?
    ▲ 11HardikVala449d💬 1
  48. 48
    DLLM: Minimal, clean coding agent built directly on llama.cpp without overheadgithub.com
    ▲ 9teleforce65d💬 3
  49. 49
    We Found a Heap Overflow in Llama.cpp's Tokenizerpwno.io
    ▲ 9retr0reg475ddiscuss
  50. 50
    Show HN: I Built an Image Captioning Tool Using Llama.cppgithub.com
    ▲ 8paradox460301d💬 1
  51. 51
    Llama.cpp now has an official website: llama.appllama.app
    ▲ 7wronglebowski140d💬 1
  52. 52
    DeepSeek-R1 speeds up llama.cpp code by x2github.com
    ▲ 6roboboffin626d💬 3
  53. 53
    Llama-macOS – Agentic and MCP Native macOS Front End for Llama.cppgithub.com
    ▲ 6car60d💬 2
  54. 54
    I patched llama.cpp to gain 20% prompt processing TPS. Help me make a PR
    ▲ 6i_am_rocoe111d💬 2
  55. 55
    Apples to Apples: MLX vs. Llama.cpp for Gemma 4 12B on an M1 16GBziraph.com
    ▲ 6ABS133d💬 1
  56. 56
    Llama.cpp AI Performance with the GeForce RTX 5090www.phoronix.com
    ▲ 6mfiguiere627d💬 1
  57. 57
    Ollama vs. Llama.cpp – Quick Benchmarkblawg.pages.dev
    ▲ 6caveman2396ddiscuss
  58. 58
    Show HN: Run Llama.cpp In-Process from Java with Project Panama FFMdeemwar-products.github.io
    ▲ 6deemwar133ddiscuss

Keyboard shortcuts

j / k
next / previous story
o or Enter
open the story
c
open the comments
s
save for later
h
history & saved stories
?
show this help