NVFP4 checkpoints without `_quantization_metadata` load silently as unquantized and crash in F.linear (LTX-2.5 nvfp4)

[desvaters]

Custom Node Testing

• I have tried disabling custom nodes and the issue persists (see how to disable custom nodes if you need help)

Expected Behavior

Loading an NVFP4-quantized diffusion model via UNETLoader should either

1. detect the quantization from the weight_scale / weight_scale_2 / input_scale tensors present in the file and load it through MixedPrecisionOps, or
2. fail loudly with a message that names the actual problem.

Actual Behavior

Neither happens. Lightricks/LTX-2.5's official diffusion_models/ltx-2.5-22b-distilled-transformer-nvfp4.safetensors loads "successfully", all 3528 quantization scale tensors are silently thrown away, and sampling then dies on the first attention projection of the first transformer block:

RuntimeError: mat1 and mat2 shapes cannot be multiplied (3520x4096 and 2048x4096)

2048 is exactly half of the model's hidden dim 4096 — it is the packed FP4 weight [out, in/2] (uint8, two values per byte) being handed to torch.nn.functional.linear as if it were a real weight matrix.

The only hint that anything went wrong is a [WARNING] unet unexpected: [...] line listing 3528 keys, which is one single ~198 KB line in the log and easy to miss. Note the asymmetry in the log — the text encoder gets a quantization path, the diffusion model does not:

[INFO] Found quantization metadata version 1          <- text encoder only
[INFO] Using MixedPrecisionOps for text encoder
...
[INFO] model weight dtype torch.bfloat16, manual cast: None    <- UNET: no quant path
[INFO] model_type FLUX
[WARNING] unet unexpected: ['transformer_blocks.0.attn1.to_q.input_scale',
          'transformer_blocks.0.attn1.to_q.weight_scale_2',
          'transformer_blocks.0.attn1.to_q.weight_scale', ... ]   <- 3528 keys dropped

There is no unet missing: line — the packed weights themselves were accepted. Only the scales were dropped.

Steps to Reproduce

1. ComfyUI 0.32.0, Blackwell GPU (NVFP4 compute supported).
2. Download diffusion_models/ltx-2.5-22b-distilled-transformer-nvfp4.safetensors from https://huggingface.co/Lightricks/LTX-2.5 (18.7 GB).
3. Open the stock video_ltx2_5_t2v template that ships with ComfyUI 0.32.0.
4. In the subgraph's UNETLoader, change unet_name from ltx-2.5-22b-distilled-transformer-comfy-int8-convrot.safetensors to ltx-2.5-22b-distilled-transformer-nvfp4.safetensors. Change nothing else.
5. Queue. It fails at SamplerCustomAdvanced at step 0.
   Reproduces regardless of weight_dtype on the loader (default / fp8_e4m3fn / fp8_e5m2), sampler, sigmas, CFG or resolution — none of those are related.

The state dict of that file:

dtype	count	role
U8	1176	packed 4-bit weights, [out, in/2]
F8_E4M3	1176	weight_scale (block scales, group size 16)
F32	1176 + 1176 + 290	weight_scale_2, input_scale, misc
BF16	2882	unquantized remainder

1176 = 42 blocks × 28 linear modules. Layer names carry the model.diffusion_model. prefix. Its __metadata__ contains only ['config', 'gemma_source_checkpoint', 'license', 'model_version'].

Debug Logs

[INFO] got prompt
[INFO] Model LTXAV prepared for dynamic VRAM loading. 24592MB Staged. 0 patches attached. Force pre-loaded 608 weights: 3303 KB.
  0%|          | 0/8 [00:00<?, ?it/s,   Model Initializing ...  ]
[ERROR] !!! Exception during processing !!! mat1 and mat2 shapes cannot be multiplied (3520x4096 and 2048x4096)
[ERROR] Traceback (most recent call last):
  File "/opt/comfyui/execution.py", line 545, in execute
    output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
                                                              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/comfyui/execution.py", line 344, in get_output_data
    return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/comfyui/execution.py", line 318, in _async_map_node_over_list
    await process_inputs(input_dict, i)
  File "/opt/comfyui/execution.py", line 306, in process_inputs
    result = f(**inputs)
             ^^^^^^^^^^^
  File "/opt/comfyui/comfy_api/internal/__init__.py", line 149, in wrapped_func
    return method(locked_class, **inputs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/comfyui/comfy_api/latest/_io.py", line 1990, in EXECUTE_NORMALIZED
    to_return = cls.execute(*args, **kwargs)
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/comfyui/comfy_extras/nodes_custom_sampler.py", line 1063, in execute
    samples = guider.sample(noise.generate_noise(latent), latent_image, sampler, sigmas, denoise_mask=noise_mask, callback=callback, disable_pbar=disable_pbar, seed=noise.seed)
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/comfyui/comfy_extras/nodes_lt.py", line 1073, in sample
    return super().sample(noise, latent_image, *args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/comfyui/comfy/samplers.py", line 1335, in sample
    output = executor.execute(noise, latent_image, sampler, sigmas, denoise_mask, callback, disable_pbar, seed, latent_shapes=latent_shapes)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/comfyui/comfy/patcher_extension.py", line 113, in execute
    return self.original(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/comfyui/comfy/samplers.py", line 1262, in outer_sample
    output = self.inner_sample(noise, latent_image, device, sampler, sigmas, denoise_mask, callback, disable_pbar, seed, latent_shapes=latent_shapes)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/comfyui/comfy/samplers.py", line 1237, in inner_sample
    samples = executor.execute(self, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar)
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/comfyui/comfy/patcher_extension.py", line 113, in execute
    return self.original(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/comfyui/comfy/samplers.py", line 1005, in sample
    samples = self.sampler_function(model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar, **self.extra_options)
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/torch/utils/_contextlib.py", line 124, in decorate_context
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/opt/comfyui/comfy/k_diffusion/sampling.py", line 218, in sample_euler_ancestral
    return sample_euler_ancestral_RF(model, x, sigmas, extra_args, callback, disable, eta, s_noise, noise_sampler)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/torch/utils/_contextlib.py", line 124, in decorate_context
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/opt/comfyui/comfy/k_diffusion/sampling.py", line 248, in sample_euler_ancestral_RF
    denoised = model(x, sigmas[i] * s_in, **extra_args)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/comfyui/comfy/samplers.py", line 640, in __call__
    out = self.inner_model(x, sigma, model_options=model_options, seed=seed)
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/comfyui/comfy/samplers.py", line 1208, in __call__
    return self.outer_predict_noise(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/comfyui/comfy/samplers.py", line 1215, in outer_predict_noise
    ).execute(x, timestep, model_options, seed)
      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/comfyui/comfy/patcher_extension.py", line 113, in execute
    return self.original(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/comfyui/comfy_extras/nodes_lt.py", line 1080, in predict_noise
    return super().predict_noise(x, timestep, model_options, seed)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/comfyui/comfy/samplers.py", line 1218, in predict_noise
    return sampling_function(self.inner_model, x, timestep, self.conds.get("negative", None), self.conds.get("positive", None), self.cfg, model_options=model_options, seed=seed)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/comfyui/comfy/samplers.py", line 620, in sampling_function
    out = calc_cond_batch(model, conds, x, timestep, model_options)
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/comfyui/comfy/samplers.py", line 211, in calc_cond_batch
    return _calc_cond_batch_outer(model, conds, x_in, timestep, model_options)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/comfyui/comfy/samplers.py", line 219, in _calc_cond_batch_outer
    return executor.execute(model, conds, x_in, timestep, model_options)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/comfyui/comfy/patcher_extension.py", line 113, in execute
    return self.original(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/comfyui/comfy/samplers.py", line 335, in _calc_cond_batch
    output = model.apply_model(input_x, timestep_, **c).chunk(batch_chunks)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/comfyui/comfy/model_base.py", line 203, in apply_model
    return comfy.patcher_extension.WrapperExecutor.new_class_executor(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/comfyui/comfy/patcher_extension.py", line 113, in execute
    return self.original(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/comfyui/comfy/model_base.py", line 247, in _apply_model
    model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, **extra_conds)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py", line 1778, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py", line 1789, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/comfyui/comfy/ldm/lightricks/av_model.py", line 1097, in forward
    return super().forward(
           ^^^^^^^^^^^^^^^^
  File "/opt/comfyui/comfy/ldm/lightricks/model.py", line 966, in forward
    return comfy.patcher_extension.WrapperExecutor.new_class_executor(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/comfyui/comfy/patcher_extension.py", line 113, in execute
    return self.original(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/comfyui/comfy/ldm/lightricks/model.py", line 1019, in _forward
    x = self._process_transformer_blocks(
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/comfyui/comfy/ldm/lightricks/av_model.py", line 997, in _process_transformer_blocks
    vx, ax = block(
             ^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py", line 1778, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py", line 1789, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/comfyui/comfy/ldm/lightricks/av_model.py", line 283, in forward
    attn1_out = self.attn1(norm_vx, pe=v_pe, mask=self_attention_mask, transformer_options=transformer_options)
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py", line 1778, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py", line 1789, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/comfyui/comfy/ldm/lightricks/model.py", line 466, in forward
    q = self.to_q(x)
        ^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py", line 1778, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py", line 1789, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/comfyui/comfy/ops.py", line 567, in forward
    return self.forward_comfy_cast_weights(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/comfyui/comfy/ops.py", line 562, in forward_comfy_cast_weights
    return torch.nn.functional.linear(input, weight, bias)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: mat1 and mat2 shapes cannot be multiplied (3520x4096 and 2048x4096)

[INFO] Prompt executed in 0.62 seconds

Other

This bug report was translated into English by Claude Opus 5 because English isn't my primary language; I reviewed its contents, so I hope it does not count as "AI slop" :)

[coderabbitai]

🔗 Related PRs

#15499 - Add support for LTX 2.5 [merged]

---

🧪 Issue enrichment is currently in open beta.

You can configure auto-planning by selecting labels in the issue_enrichment configuration.

To disable automatic issue enrichment, add the following to your .coderabbit.yaml:

issue_enrichment:
  auto_enrich:
    enabled: false

💬 Have feedback or questions? Drop into our discord!