Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Login
Top
New
Best
Ask
Show
Jobs
1.
▲
Pass-grave: extension for pass to easily hide the metadata of the password store
(github.com/8go)
1 point
yc99
7 years ago
discuss
2.
▲
Pass-backup: extension for pass to easily create backups of the password store
(github.com/8go)
1 point
yc99
7 years ago
discuss
3.
▲
A bash script (CLI) for displaying crypto currencies market data in a terminal
(github.com/8go)
1 point
yc99
9 years ago
discuss
4.
▲
Prime number sets as mathematical sequence based on sine products
(github.com/8HoLoN)
5 points
8HoLoN
4 years ago
1 comment
5.
▲
Show HN: Hebo Gateway, an embeddable AI gateway with OpenAI-compatible endpoints
(github.com/8monkey-ai)
3 points
dselvaggio
4 months ago
discuss
6.
▲
I create guided example on Traefik with Pomerium identity-aware access proxy
(github.com/8gears)
3 points
VadimBauer
6 years ago
discuss
7.
▲
Show HN: OpenTangl – Autonomous AI dev engine for multi-repo products
(github.com/8co)
1 point
8con
3 months ago
discuss
8.
▲
Show HN: Run Qwen3-Next-80B on 8GB GPU at 1tok/2s throughput
(github.com/Mega4alik)
123 points
anuarsh
9 months ago
17 comments
9.
▲
AirLLM enables 8GB MacBook run 70B LLM
(github.com/lyogavin)
79 points
SlavikCA
2 years ago
13 comments
10.
▲
30B model now needs only 5.8GB of RAM? How?
(github.com/ggerganov)
31 points
olalonde
3 years ago
11 comments
11.
▲
Show HN: L88 – A Local RAG System on 8GB VRAM (Need Architecture Feedback)
12 points
adithyadrdo
3 months ago
3 comments
12.
▲
Show HN: Like grep but for natural questions. Mixtral 8x7B – 28 tok/s on 8GB GPU
(github.com/moritztng)
10 points
molli
2 years ago
discuss
13.
▲
Show HN: Moondream, a small vision language model that runs on 8GB of RAM
(github.com/vikhyat)
9 points
radq
2 years ago
discuss
14.
▲
Show HN: Run gpt-oss-20b on 8GB GPUs
(github.com/Mega4alik)
6 points
anuarsh
9 months ago
discuss
15.
▲
I built an AI browser with prompt-injection defense at 16 on an i5 with 8GB RAM
3 points
latestinssan
3 months ago
discuss
16.
▲
Show HN: L88 – A Local RAG System on 8GB VRAM (Need Architecture Feedback)
(github.com/Hundred-Trillion)
3 points
adithyadrdo
3 months ago
discuss
17.
▲
Show HN: Fine-tune Llama3-8B on 8GB GPU without quantization
(github.com/Mega4alik)
3 points
anuarsh
7 months ago
discuss
18.
▲
Show HN: Parakeet LLM Demo (378M param. 8GB VRAM)
2 points
razodactyl
2 years ago
discuss
19.
▲
Expired Github.com RSA Certificate
(testtls.com)
2 points
8organicbits
3 years ago
discuss
20.
▲
Logicbone: Lattice FPGA Devboard with 8GB RAM
(github.com/oskirby)
2 points
zdw
6 years ago
discuss
21.
▲
Show HN: Realtime LLM Chat on an 8GB Nvidia GPU
(github.com/andybarry)
1 point
z991
3 years ago
discuss
22.
▲
Ppa:ondrej/php is unstable for a moment due 8GB limit
(github.com/oerdnj)
1 point
screeny05
9 years ago
discuss
23.
▲
Show HN: Mastra – Open-source JS agent framework, by the developers of Gatsby
(github.com/mastra-ai)
442 points
calcsam
a year ago
154 comments
24.
▲
Show HN: Open-source, browser-local data exploration using DuckDB-WASM and PRQL
(github.com/pretzelai)
227 points
prasoonds
2 years ago
74 comments
25.
▲
Show HN: Supavisor – a Postgres connection pooler written in Elixir
(github.com/supabase)
149 points
kiwicopple
3 years ago
49 comments
26.
▲
Launch HN: Patterns (YC S21) – A much faster way to build and deploy data apps
149 points
kvh
4 years ago
36 comments
27.
▲
Show HN: We Put Chromium on a Unikernel (OSS Apache 2.0)
(github.com/onkernel)
132 points
juecd
a year ago
46 comments
28.
▲
Show HN: I compressed 10k PDFs into a 1.4GB video for LLM memory
(github.com/Olow304)
61 points
saleban1031
a year ago
23 comments
29.
▲
Show HN: Fine-tuned Llama 3.2 3B to match 70B models for local transcripts
(bilawal.net)
31 points
phantompeace
9 months ago
8 comments
30.
▲
Show HN: Heygem AI – An Open Source, Free Alternative to Heygen AI
(github.com/duixcom)
24 points
heygem-ai-new
a year ago
3 comments
More