A tiny LLM running at 21,000 tok/s on a $250 FPGA (Live Demo)
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.
Want to reach these readers? Sponsor an issue.
HN · launched Aug 10, 2026 · 79 upvotes (top 9%) · 0 views
Niche: llm inference engines · 133 launches, 4 in the last 7 days ▼ -33% · Explore this niche →
Category and tags
- Horizontal
- Model & infra
- Developer
- AI-native
- Hobby / open-source project
Visit website ↗ Source listing ↗
More like this: all 133 launches in llm inference engines →
Could you build this?
No This project implements custom hardware HDL to execute an LLM directly on an FPGA chip with on-chip weights reaching tens of thousands of tokens per second. Building FPGA-based deep learning accelerators requires specialized digital hardware design (Verilog/VHDL/Chisel) and computer architecture expertise.
What it would actually take: The system requires designing a custom hardware matrix-vector multiplication pipeline in RTL (Verilog/VHDL or Bluespec), memory controller interfaces to FPGA BRAM/URAM, and custom quantization/weight-packing schemes. The core difficulty is timing closure, pipeline stalling mitigation, and resource utilization optimization under hardware constraints on a budget FPGA. This demands expert hardware and embedded systems engineers.
Discussion
20 comments analyzed.
Competitors mentioned: Cactus models, Alveo V80, GPUs for inference, ASICs, CIM/analog-compute startups
Concerns raised: FPGAs are niche with small total market volume, Can't cost-effectively compete with other options for LLM inference, Model too large for time series/sensor data processing, HLS is a dead-end approach, FPGA vendors optimize for larger chips, not cost-effectiveness
Feature requests: Make four ROMs boot-loadable for hot-swapping models without reconfiguration, Dynamic partial reconfiguration to avoid full bitstream reloads, Support for novel memory technologies for weight storage, Better tooling than HLS and SystemVerilog
Competitors
Other products that read as similar to this one : 777 launches clear the similarity bar, closest 8 shown.
Attention rank: #81 of 778 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).
Launched 281 days after the earliest competitor.
- Minimal LLM Post-Training Experiments on an 8GB GPU (SFT, DPO, GRPO) · hn · 2026-08-01 · 21 upvotes · similarity 0.58
- PocketOrca-LLM · github · 2026-09-14 · 8 upvotes · similarity 0.57
- A tiny C program where an LLM rewires its DAG while running · hn · 2026-05-05 · 15 upvotes · similarity 0.55
- Llmspeed · hn · 2026-10-17 · 329 upvotes · similarity 0.55
- Spectra Super Intelligence · ph · 2026-10-17 · 1 upvotes · similarity 0.52
- unixpc · github · 2026-11-06 · 27 upvotes · similarity 0.52
- BootLife · github · 2026-09-20 · 55 upvotes · similarity 0.50
- Silver · ph · 2026-11-04 · 1 upvotes · similarity 0.50
The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.