publisher

inference-optimization

0 builds measured across 3 families, and 4 derivatives of other people's models. Ranked by what machines proved, never by downloads.

derivatives — changes this publisher made to someone else's weightsGLM-5-2.9B-A2.8B-smallglm-5 GLM-5.2-0.8B-A0.8Bglm-5-2 GLM-5.2-0.8B-A0.8Bglm-5-2 Kimi-K3-0.40Bkimi-k3

in the catalog, not yet measured — declared, unsignedinference-optimization/GLM-5-2.9B-A2.8B-smallglm-5/base~inference-optimization-a2-8b-small · BF16 · vllm · derivative inference-optimization/GLM-5.2-0.8B-A0.8Bglm-5-2/base~inference-optimization-a0-8b · FP32 · vllm · derivative inference-optimization/Kimi-K3-0.40Bkimi-k3/base~inference-optimization · FP32 · vllm · derivative