Verified65% confidenceBenchmarkExact time
Memory requirements are at least 37.6 GB for Q2_0, at least 39.2 GB for IQ2_XS, and at least 47 GB for IQ3_XXS, with the vision encoder occupying an additional 0.91 GB.
3
Sources
65%
Confidence
Medium-term (~90 days)
Relevance
9/24/2026
First Seen
Valid until: 12/23/2026
Sources
Related Entities
Related Claims
Unverified使用IQ4_XS配合-fa 1 -ctk q8_0 -ctv q8_0对KV缓存进行q8_0量化后，可加载完整32k上下文，常驻内存约16.6GB78% similarUnverifiedIQ2_XS can compress a model to close to 2 bits/weight, enabling a 70B model that would otherwise require 48 GB of VRAM to fit into a 24 GB consumer-grade GPU78% similarUnverifiedAround 36 GB of RAM is recommended for the Q2 version, while 64 GB or more (with weights larger than 43 GB) allows for higher-precision versions.76% similarUnverifiedFor a model of approximately 160 GB (such as the UD-Q3_K_XL quantized version of Qwen3.5-397B), running the lens requires approximately 20 GB of additional memory.75% similarUnverifiedIQ4_XS量化文件大小15.57GB，pp2048为95.4 tok/s，tg128为10.9 tok/s73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/948584API
curl https://kongchang.com/api/v1/knowledge/claims/948584MCP
get_claim(id=948584)