Heykuki News

TopNewBestAskShowJobs
TopNewBestAskShowJobs
31.
Show HN: KTransformers–236B Model and 1M Context LLM Inference on Local Machines (github.com/kvcache-ai)
20 points
sssummer
2 years ago
3 comments
32.
Show HN: KTransformers:671B DeepSeek-R1 on a Single Machine-286 tokens/s Prefill (github.com/kvcache-ai)
14 points
sssummer
a year ago
discuss
33.
Show HN: Bonsai 1.7B ternary model at 442T/s on M4 Max (agents2agents.ai)
13 points
hhuytho
a month ago
3 comments
34.
Show HN: RoundtableJS – Open-source programmatic survey library (github.com/roundtableAI)
13 points
timshell
2 years ago
1 comment
35.
Show HN: Off Grid: On-device AI-web browsing, tools vision,image,voice–3x faster
12 points
ali_chherawalla
3 months ago
5 comments
36.
Show HN: OneUptime (New Update) – Open-Source Datadog Alternative
8 points
devneelpatel
2 years ago
6 comments
37.
Show HN: Quickwit – OSS Alternative to Datadog, Elasticsearch (github.com/quickwit-oss)
8 points
francoismassot
2 years ago
2 comments
38.
Tq-KV – Rust implementation of TurboQuant that works on GGUF models
3 points
onurgokyildiz
2 months ago
discuss
39.
Show HN: Configurable Open Source Audio Spectrum Analyzer (github.com/sylwekkominek)
3 points
sylwekkominek
9 months ago
discuss
40.
Show HN: iceoryx2 v0.3.0 released – zero-copy IPC middleware in Rust (github.com/eclipse-iceoryx)
3 points
elfenpiff
2 years ago
discuss
41.
Show HN: Open dataset of real-world LLM performance on Apple Silicon (devpadapp.com)
2 points
uncSoft
3 months ago
4 comments
42.
Ask HN: How would you design an interface where artworks come alive with story?
2 points
dejicarr
7 months ago
2 comments
43.
Show HN: Loft CLI – Fine-tune and run LLMs (1–3B) on 8 GB MacBook Air, no GPUs
2 points
dips2umar
10 months ago
1 comment
44.
Show HN: NeuG – High-performance Embedded graph DB, one line to serve
2 points
robeenly
a month ago
discuss
45.
Sumi – Open-source voice-to-text with local AI polishing
2 points
alkd
3 months ago
discuss
46.
Show HN: I wrote an LLM inference engine in pure Go – 48 tok/s zero dependencies (github.com/computerex)
2 points
computerex
3 months ago
discuss
47.
Show HN: OctoFlow v1.0.0 – GPU VM where the GPU runs autonomously, CPU is BIOS
2 points
mr_octopus
3 months ago
discuss
48.
Show HN: I maintain Valkey GLIDE – built a Node queue doing 48k jobs/s (github.com/avifenesh)
2 points
anotherCodder
3 months ago
discuss
49.
Show HN: A private, PQ-secure, infinitely scalable blockchain[fully open-source] (github.com/nerv-bit)
2 points
Nerv_b
4 months ago
discuss
50.
Ask HN: Is there an open-source Git-backed multi-tenant wiki?
2 points
ponsfrilus
6 years ago
discuss
51.
Seeking grant proposals $250k total budget for privacy blockchain tech projects
2 points
exolymph
8 years ago
discuss
52.
A small tool I made for local LLMs: LLM-neofetch-plus
1 point
HFerrahoglu
3 months ago
2 comments
53.
Ollama and Bifrost –> Qwen3 in Claude Code
1 point
all2
9 months ago
2 comments
54.
Ask HN: Best LLM model for a RAG-based Android app across all smartphones?
1 point
swaminarayan
2 months ago
1 comment
55.
Off Grid: On-device AI-web browsing, tools, vision, image gen, voice – 3x faster
1 point
ali_chherawalla
3 months ago
1 comment
56.
Ask HN: GitHub-based spam/scam emails
1 point
munchor
13 years ago
discuss
57.
Show HN: WayInfer – Native GGUF engine that runs models larger than your RAM
1 point
ahmedm24
2 months ago
discuss
58.
Show HN: Go LLM inference with a Vulkan GPU back end that beats Ollama's CUDA (github.com/computerex)
1 point
computerex
3 months ago
discuss
59.
Show HN: Voxtral Mini 4B Realtime running in the browser (github.com/TrevorS)
1 point
adefa
4 months ago
discuss
60.
Show HN: Open-source multi-agent subtitle translator (self-hosted) (github.com/subtitlesdog)
1 point
mrqjr
4 months ago
discuss
More