# SigmanticAI/apex-inference-chip

<https://repo.masters-masters.com/en/repos/SigmanticAI/apex-inference-chip>

[Home](https://repo.masters-masters.com/en) › [SigmanticAI](https://repo.masters-masters.com/en/owners/SigmanticAI) › [apex-inference-chip](https://repo.masters-masters.com/en/repos/SigmanticAI/apex-inference-chip)

SigmanticAI/apex-inference-chip has 555 stars on GitHub. Its RepoMasters card: Alpha tier. An inference chip design that runs a real LLM (Qwen2.5-0.5B) on…

| Field | Value |
| --- | --- |
| Owner | [SigmanticAI](https://repo.masters-masters.com/en/owners/SigmanticAI) |
| Stars | 555 |
| Forks | 13 |
| Language | [Python](https://repo.masters-masters.com/en/languages/python) |
| License | Apache-2.0 |
| Created | 2026 |
| Tier | [Alpha (250 to 699 ★)](https://repo.masters-masters.com/en/ranks/b_movie) |
| View on GitHub | [SigmanticAI/apex-inference-chip](https://github.com/SigmanticAI/apex-inference-chip) |

## Repository

An inference chip design that runs a real LLM (Qwen2.5-0.5B) on FPGA — one transformer decoder layer in RTL, every silicon value bit-exact against a golden model. 0.56 tok/s measured, a 140× climb, full evidence trail.

The tier for repos with 250 to 699 ★. Published odds per card pulled: 20%. Rarity: Uncommon.

## Nearby in Python

- [Gajesh2007/ai-trading-agent · ★ 555 · Python · Alpha](https://repo.masters-masters.com/en/repos/Gajesh2007/ai-trading-agent)
- [mshumer/unslop · ★ 555 · Python · Alpha](https://repo.masters-masters.com/en/repos/mshumer/unslop)
- [microsoft/Orchard-Agentic · ★ 555 · Python · Alpha](https://repo.masters-masters.com/en/repos/microsoft/Orchard-Agentic)
- [jbardin/scp.py · ★ 555 · Python · Alpha](https://repo.masters-masters.com/en/repos/jbardin/scp.py)
- [firstlookmedia/pdf-redact-tools · ★ 555 · Python · Alpha](https://repo.masters-masters.com/en/repos/firstlookmedia/pdf-redact-tools)
- [QubesOS/qubes-secpack · ★ 555 · Python · Alpha](https://repo.masters-masters.com/en/repos/QubesOS/qubes-secpack)

---
Data: GitHub · Illustration drawn by RepoMasters from the repo’s ID and its language color.