v1.0.0 — Qwen3.8-Flash-Next, sushi-packed
Add support for 2 sushi models
- Qwen3.8-Flash-Next-Sushi-3bpw (requires 64 GB+)
- Qwen3.8-Flash-Next-Sushi-4bpw (requires 96 GB+)
Quality
KLD against the bf16 model: 16 prompts x 512 tokens scored to the first EOS, kv8, every pack run by the same sushi
build. The light rings are the sushi packs with a 4-bit n-gram table (Sushi-3bpw ships that table; either table works
with either pack). Numbers: docs/quality-kld.md.
Speed
Sushi-3bpw on an M5 Max 128 GB, sushi v1.0.0 release candidate (build 725b76c): --ctx-size 1048576 --kv-quant 8 --mtp, llmprobe --bench-only, quiet box.