Unverified50% confidenceFactExact time
Of this 125B model's backbone, approximately 121B is the Mixture-of-Experts (MoE) portion, with an additional approximately 51B PLE lookup table and approximately 4B MTP module, bringing the complete checkpoint close to 180B.
1
Sources
50%
Confidence
Long-term
Relevance
10/5/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe open-source project claims that the 125B model quantized with IQ3 can run on consumer-grade hardware consisting of a 12GB VRAM GPU plus 32GB or more of CPU memory.67% similarUnverifiedQwen3.5-122B-A10B is a MoE architecture model with approximately 122B total parameters and approximately 10B activated parameters.65% similarUnverifiedOn dense mid-scale models (such as 27B), the AMD R9700 leads significantly; on MoE models the two are roughly on par; and on small workloads the B70 has a slight edge.64% similarUnverifiedThe MiniCPM-2B model supports a 131K context62% similarUnverifiedThe full weights of LLaMA 2 (70B parameter version) amount to approximately 130 GB.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/978652API
curl https://kongchang.com/api/v1/knowledge/claims/978652MCP
get_claim(id=978652)