| { |
| "format": "qwen35-9b-ttnn-native-text-v1", |
| "scope": "text-only-no-vision-with-mtp", |
| "precision_groups": { |
| "torch.bfloat16": { |
| "tensors": 193, |
| "parameters": 1261466880, |
| "serialized_tensor_bytes": 2522954504 |
| }, |
| "torch.float32": { |
| "tensors": 48, |
| "parameters": 3840, |
| "serialized_tensor_bytes": 20160 |
| }, |
| "bfp8": { |
| "tensors": 195, |
| "parameters": 5217714176, |
| "serialized_tensor_bytes": 5543891512 |
| }, |
| "bfp4": { |
| "tensors": 54, |
| "parameters": 2717908992, |
| "serialized_tensor_bytes": 1528843248 |
| } |
| }, |
| "artifact_bytes": 9629415772, |
| "tensor_parameters": 9197093888, |
| "quantizer": "TTNN native BFP4_B/BFP8_B rounding with selectively retained precision; not the Unsloth quantizer", |
| "calibration": "300941 chat-templated input tokens; activation second moments propose precision, validation output KL selects it", |
| "embedding": "Original BF16 retained", |
| "nonlinear": "All 48 original FP32 GDN norm/A_log tensors retained losslessly", |
| "limitations": [ |
| "Single Blackhole P150; text-only with MTP-1, no vision", |
| "Native TT format, not GGUF or bitsandbytes", |
| "Local validation gates are not official Unsloth benchmark thresholds" |
| ], |
| "mtp": { |
| "tensors": 15, |
| "serialized_bytes": 486582864, |
| "storage": "All original draft tensors preserved losslessly at source dtype", |
| "runtime": "Existing draft attention and MLP BFP4 policy retained; FC and norms BF16; shared embedding BF16 and shared target LM head BFP8", |
| "runtime_precision_binding": "Mode-specific equivalence runtime_environment and runtime_sources; target precision map does not apply to draft layers" |
| } |
| } |
|
|
