AI is happening. The future is updating.DeepSeek-V4-Flash-imatrix-aligned
These are quants for the DS4 inference engine, built with an importance matrix (imatrix) and with tensor offsets aligned for efficient mmap on Apple Silicon. They are a drop-in replacement for the files published in antirez/deepseek-v4-gguf, with two changes: The MTP file is reproduced here unchanged so a single repo holds everything `download_model.sh` expects. Use the IQ2XXS quant on 128 GB Mac machines, pair it with the MTP file for optional speculative decoding.
These are quants for the DS4 inference engine, built with an importance matrix (imatrix) and with tensor offsets aligned for efficient mmap on Apple Silicon. They are a drop-in replacement for the files published in antirez/deepseek-v4-gguf, with two changes: The MTP file is reproduced here unchanged so a single repo holds everything `download_model.sh` expects. Use the IQ2XXS quant on 128 GB Mac machines, pair it with the MTP file for optional speculative decoding.