Unverified50% confidenceFactExact time
For repositories without a config.json, ModelFit uses a fixed overhead rule of "about 20% + 1.5GB" and marks this on the page, so the numbers for these models are still estimates.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/17/2026
First Seen
Valid until: 1/15/2027
Sources
Related Entities
Related Claims
UnverifiedWhen config.json is available, ModelFit uses the GQA formula to precisely calculate the KV cache: 2 × layers × kv_heads × head_dim × ctx × 2 bytes; otherwise it uses the heuristic rule of "+20% with a minimum of 1.5GB" and clearly marks this on the page.69% similarUnverifiedMeta's LLaMA 2 70B model still requires approximately 35 GB of VRAM to fully load even with 4-bit quantization.64% similarUnverifiedFreeToken实测8GB显存笔记本可运行约35B参数模型64% similarUnverifiedA 125-billion-parameter model can run on 12G of VRAM, relying mainly on model quantization and a mixture-of-experts (MoE) architecture, achieved by activating only part of the expert parameters, quantizing weights to 4bit or lower, and dynamically loading inactive parameters from memory or SSD on demand.63% similarVerifiedThe model weights alone of a 175-billion-parameter model (in BF16 precision) require 350 GB of storage, and the Adam optimizer must maintain two sets of states—first-order moments and second-order moments—totaling more than 1 TB.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1054748API
curl https://kongchang.com/api/v1/knowledge/claims/1054748MCP
get_claim(id=1054748)