kindi
A custom LLM inference engine for low-cost NVIDIA GPUs: Quadro K420 and K1200, two K1200s joined into one 8 GB card, GTX 1080 and RTX 3080. Runs Bonsai 2B, 4B, 9B and 27B models with an OpenAI-compatible server.
Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.
Visit website ↗ Source listing ↗
GITHUB · launched Oct 20, 2026 · 36 upvotes (top 36%)
- Horizontal
- Model & infra
- Developer
- AI-native
- Hobby / open-source project
- ampere
- bitnet
- cuda
- kepler
- llm-inference
- local-llm
- +7 more in the details below
Similar launches
See all 3346 similar launches →Could you build this?
No It requires low-level GPU kernel work for a legacy card with 1 GB of memory, plus model quantization and inference optimization that vibe coding cannot substitute for.
What it would actually take: The project needs a custom inference runtime written against the GPU's compute stack, with hand-tuned kernels for ternary or low-bit weights. It also needs deep knowledge of quantized model formats, memory-constrained scheduling, and benchmarking against llama.cpp. Experienced systems and GPU programmers are required.
Competitors
Other products that read as similar to this one : 3346 launches clear the similarity bar, closest 8 shown.
Attention rank: #1124 of 3347 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).
Launched 356 days after the earliest competitor.
- open_rknpu2_lm_infer · github · 2026-10-14 · 13 upvotes · similarity 0.78
- Tiny-vLLM · hn · 2026-05-29 · 205 upvotes · similarity 0.77
- strixite · github · 2026-10-04 · 11 upvotes · similarity 0.76
- Open-source AMDGCN kernels for optimizing LLM inference · hn · 2026-08-25 · 5 upvotes · similarity 0.73
- Infernix · github · 2026-10-08 · 98 upvotes · similarity 0.70
- Goku · hn · 2026-07-15 · 9 upvotes · similarity 0.69
- TandemLLM · github · 2026-09-28 · 21 upvotes · similarity 0.67
- nano-deepinfer · github · 2026-10-20 · 16 upvotes · similarity 0.67
Other launches for this product
- No other launches for this product.
More details
- External ID
- 1426323151
- Company
- n/a
- Product
- kindi
- Website domain
- amirhusain.com
- Cohort
- n/a
- Upvotes percentile
- 0.64
- All tags
- ampere, bitnet, cuda, kepler, llm-inference, local-llm, low-cost-gpu, maxwell, openai-compatible, pascal, quadro, tensor-parallelism, ternary
- AI summary
- llm inference engine for nvidia quadro k420 gpus
- Manually corrected
- No