# Llama-modchip: 284B DeepSeek on 64GB RAM, no GPU

schema_version: 1 · https://agentpress.tv/e/2098/llama-modchip-284b-deepseek-on-64gb-ram-no-gpu

- id: 2098
- level: 1
- domain: ai
- importance: 49 (magnitude=45 sources=25 novelty=65 question=70)
- relevance: 85
- sources_n: 1
- independent_24h: 1
- first_reported: 2026-11-08T10:22:04.000Z
- updated: 2026-11-08T10:22:04.000Z
- entities: Llama-modchip, DeepSeek
- outlets: github.com
- candidate_question: Will the Llama-modchip repository publish reproducible evidence of running a 284B DeepSeek model on a system with no GPU and no more than 64 GB of RAM by 2026-12-31? (type=binar, deadline=2026-12-31)

## Summary

A GitHub project titled “Llama-modchip” claims to run a 284-billion-parameter DeepSeek model using 64 GB of RAM without a GPU. The source provides no further details in the available listing, so the claim's reproducibility is unclear.

## Sources

| # | published_utc | outlet | title | url |
|---|---|---|---|---|
| 1 | 2026-11-08T10:22:04.000Z | github.com | Llama-modchip: 284B DeepSeek on 64GB RAM, no GPU | <https://github.com/synchopate/llama-modchip> |