A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
C avx2c99cpu-inferencedeep-learningfrom-scratchinference-enginekimi-k3linear-attentionllmllm-inferencemachine-learningmemory-efficientmixture-of-expertsmoemxfp4quantizationsimdsystems-programmingtransformerzero-dependencies
| Name | Last commit message | Last commit date |
|---|---|---|
| .. | ||
| download-model.sh 14.3 KB | ||
| jetson-proof-of-life.sh 8.0 KB | ||
| k3-doctor.sh 8.1 KB | ||
| pack-trunk.sh 1.4 KB | ||
| shard_sizes.txt 4.3 KB | ||