Unverified50% confidenceFactExact time
GhostRunner can run on a laptop GPU with only 4 GB of VRAM.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/15/2026
First Seen
Valid until: 1/13/2027
Sources
Related Entities
Related Claims
UnverifiedA 4B parameter model (such as Phi-3-mini or Llama 3.2 3B) requires only approximately 8GB of VRAM and can run on a consumer-grade GPU.66% similarUnverifiedRunning a 16-bit precision 70B model on 2×80GB GPUs leaves only 2.9 GB of VRAM after the weights are loaded, accommodating only about 9,000 in-flight tokens, which in practice cannot serve requests effectively.64% similarUnverifiedNVIDIA claims that the weights of Nemotron 3.5 Bolt 74B-A9B can run in 24GB of memory, and that 24GB refers only to the weights themselves, excluding context, KV cache and runtime overhead.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1041012API
curl https://kongchang.com/api/v1/knowledge/claims/1041012MCP
get_claim(id=1041012)