Ornith-1.0-35B-NVFP4

Ornith-1.0-35B-NVFP4

This is an NVFP4/FourOverSix quantized checkpoint of deepreinforce-ai/Ornith-1.0-35B.

Quantization

• Source revision: 5df2ed3f675c7beaa490328cc70bb573b65fb660
• Format: transformers + fouroversix
• Weight dtype: nvfp4
• Scale rule: static_6
• Output dtype: bfloat16
• lm_head plus 154 shape-incompatible linear modules are kept in the original BF16 format and listed in modules_to_not_convert.

The checkpoint was converted by streaming the original safetensor shards into FourOverSix-compatible quantized tensors, so it can be loaded with recent transformers builds that include FourOverSixConfig support and the fouroversix package installed.

Loading Note

This checkpoint was smoke-tested with transformers==5.12.1, torch==2.10.0+cu130, and fouroversix==1.0.5. The local FourOverSix install also included the Qwen3.5 MoE compatibility fix for DataType property access inside fouroversix/model/modules/qwen.py. If loading raises an error such as DataType object is not callable, a missing scale_dtype, or missing get_weight_scale_rule / get_activation_scale_rule, update FourOverSix to a release containing that fix or patch that Qwen module.

Local Decode Benchmark

Tested on an NVIDIA GB10 with transformers==5.12.1, torch==2.10.0+cu130, and the patched fouroversix==1.0.5 runtime. The test used batch size 1, greedy manual decoding, synthetic repeated-token context, 1024-token chunked prefill, and logits_to_keep=1.

The 100k context run completed, but used about 120.6 GiB of the GB10's 121.7 GiB visible CUDA memory, leaving roughly 1.1 GiB free.