inference-optimization/GLM-5.3-0.6B-A0.4B

Quantization vs zai-org/GLM-5.3. zai-org/GLM-5.3 is a quantized version of the other (F8_E4M3/BF16).

1 derivatives checked

• mradermacher/GLM-5.3-0.6B-A0.4B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse