Unverified50% confidenceBenchmarkExact time
ActionAssist using IQ4 quantization occupies only 2GB of VRAM, and after offloading the remainder to system memory, it still runs faster than most comparable models.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/12/2026
First Seen
Valid until: 12/11/2026
Sources
Related Entities
Related Claims
UnverifiedIQ4_XS与Q4_K_M速度几乎一致，但IQ4_XS体积更小可节省约2GB空间用于扩展上下文，因此性价比更高69% similarUnverifiedA model with 2B parameters typically requires only about 1–2 GB of memory after INT4 quantization, enabling it to run on mainstream smartphones, embedded development boards, and similar devices.68% similarUnverifiedAfter applying INT4 quantization, the memory footprint of a 3B parameter model can be reduced to approximately 2 GB.66% similarUnverifiedA single iOS simulator instance typically requires more than 4 GB of memory.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/912380API
curl https://kongchang.com/api/v1/knowledge/claims/912380MCP
get_claim(id=912380)