Unverified50% confidenceFactExact time
The all-MiniLM-L6-v2 embedding model has about 22 million parameters, with the quantized CPU version at only 23MB and the WebGPU version at 90MB.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/14/2026
First Seen
Valid until: 1/12/2027
Sources
Related Entities
Related Claims
UnverifiedRunning MiniMax H3 on an RTX 4070 or below (12 GB or less) may require extreme optimizations such as full model offloading to CPU, reducing resolution, and decreasing frame count.71% similarUnverified2B-parameter-scale models can run on a single consumer-grade GPU (e.g., RTX 3090/4090 with 24 GB VRAM) or even in some CPU inference scenarios.70% similarUnverifiedMiniMax H3's weights total 67 GB, comprising a 34 GB DiT backbone, a 27 GB Qwen3-VL encoder, plus VAE70% similarUnverifiedA tester ran a 20.7B dense model on a dual-4090 (48 GB VRAM) workstation and achieved 27.6 tokens per second, only slightly faster than Dwarf Star, but with over 10 times fewer parameters.70% similarUnverifiedTTM 模型参数量仅约 0.8M（百万级），文件大小约三兆字节，无需 GPU，在普通 CPU 上就能运行70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1025963API
curl https://kongchang.com/api/v1/knowledge/claims/1025963MCP
get_claim(id=1025963)