Better* than glm-5.2. At home. * — before quantization, which does degrade quality
Unsloth AISmaller DeepSeek-V4-Flash quants are now available to run from 1-bit to 4-bit. Run 3-bit on 128GB RAM, 1-bit on 96GB RAM. Remember full precision is mostly FP4 (4-bit) so 1 to 3-bit are not that quantized. Even more variants are coming very soon: huggingface.co/unsloth/Deep...