sakamakismile/KAT-Coder-V2.5-Dev-NVFP4

🤗 Hugging Face sourceapache-2.020.4B params22 GBsafetensors✓ 2 checksumsupdated today
Submit in one command

Run it next to your model folder. It makes the torrent, checks your files against Hugging Face, and submits it. You just start seeding and paste your key from your account. It only reads your files and never changes them. Read the script first if you like.

curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo sakamakismile/KAT-Coder-V2.5-Dev-NVFP4 ./model-folder
Needs a seeder →

KAT-Coder-V2.5-Dev-NVFP4

NVFP4 (W4A4, compressed-tensors) quantization of Kwaipilot/KAT-Coder-V2.5-Dev — the 35B-A3B agentic-coding MoE (SWE-bench Verified 69.4% upstream).

70GB bf16 → 21.9GB. Runs on a single 24GB Blackwell card, or 2× 16GB.

Quantized by Lna-Lab (@Tono_Ken3).

Measured (12x RTX PRO 2000 Blackwell 16GB, 60W power cap each)

  • TP=2 (2 GPUs): ~122 tok/s single-stream
  • Sanity: lookahead-bias trading question answered with the correct shift(1) fix; clean O(n) implementations with tests.

Serving

vllm serve <this-repo> --tensor-parallel-size 2 --max-model-len 32768 \
  --gpu-memory-utilization 0.92
# NVFP4 is auto-detected; no --quantization flag needed.
# On no-P2P multi-GPU boxes add: NCCL_P2P_DISABLE=1, --disable-custom-all-reduce

Recipe notes

  • Arch qwen3_5_moe quantizes cleanly with llm-compressor (targets=Linear, scheme NVFP4) with these ignores: lm_head, re:.*conv1d.* (DeltaNet conv), re:.*mlp.gate$ and re:.*shared_expert_gate$ (MoE routers), re:.*mtp.*.
  • The open-weight release ships without vision and without MTP tensors (we checked; nothing to graft).
  • Calibration: 32 samples x 8192 tokens (neuralmagic/calibration), single GPU, ~4 minutes total wall.
  • Newer transformers removed GraniteMoeParallelExperts which llm-compressor still imports — a dummy class injected before import satisfies it safely for non-Granite models.

W4A4 is stable on this architecture (5th model family we've confirmed: Nex-N2, Holo, Ornith, AgentWorld, KAT).