GLM-5.3-Flash-NVFP4-CSF-QAD

A lossless NVFP4-CSF container of local-inference-lab/GLM-5.3-Flash-NVFP4 at revision 175ae8ce3b5af842b0d0140dbeb43e9cfc557c49, the GLM-5.3-Flash QAD checkpoint (NVFP4 routed experts, BF16 dense layers).

CSF stores the routed-expert block-scale planes in a compressed form. Nothing else changes: FP4 weight nibbles, every other tensor, the tensor names, dtypes, shapes and the source metadata are all byte-identical. Decoding is integer arithmetic on bytes, with no requantization or fitting. The original safetensors shards can be restored bit-exactly.

Routed experts (layers 3-44 x 288) - NVFP4 (E2M1, E4M3 scale per 16), QAD
MTP (layer 45) routed experts - MXFP8
Attention, shared experts, dense layers - BF16

Routed-expert block scales - lossless NVFP4-CSF (byte-window4-fixed-stream-u24-exceptions/1)

Sizes

• Weight files: 198.06 GB in the source, 188.87 GB here (9.19 GB saved).
• Compressed scales: 36,288 matrices (E4M3 block scales of the 42 x 288 x 3 main-layer routed-expert projections): 19.03 GB -> 9.83 GB (51.6%).

Provenance

• Source: local-inference-lab/GLM-5.3-Flash-NVFP4 revision 175ae8ce3b5af842b0d0140dbeb43e9cfc557c49, 44 index-referenced safetensors shards. During export, each source shard's SHA-256 was checked against its Hugging Face LFS hash.
• Built with trellis-quant trellis_quant.lossless_scale_checkpoint (commit 60feca330087, family glm53_nvfp4).
• verification.json: every original shard was rebuilt from this container, and both the rebuilt and the stored files matched their SHA-256 (36,288 scale matrices, 44 shards, passed).
• Files that the source index does not reference (amax.safetensors, amax_checkpoint.safetensors, model-00036-of-00036.safetensors) are not carried. vLLM never loads them.

Layout

lil-nvfp4-csf-checkpoint/1, codec byte-window4-fixed-stream-u24-exceptions/1:

• tensors/ - the source shard names; each routed-expert scale <name> is stored as <name>.nvfp4_csf_fixed (uint8) plus <name>.nvfp4_csf_exceptions (uint32)
• metadata/ - byte copies of the source's config, tokenizer, index, README and LICENSE
• config.json - a copy of metadata/config.json at the top of the repository, where the Hub counts downloads; runtimes read metadata/
• manifest.json, build-contract.json, receipts/ (per-shard source headers and hashes), verification.json
• LICENSE, NOTICE, LICENSES/ (upstream license texts), CITATION.cff, REUSE.toml, and the SHA-256 of every file in SHA256SUMS and lil-manifest.json

There is no top-level model.safetensors.index.json, so a plain safetensors loader will not open this directory by mistake.

Serving

Use vLLM with the NVFP4-CSF reader: --quantization nvfp4_csf --load-format nvfp4_csf. Point vLLM at a serving directory that holds the files of metadata/, with config.json's quantization_config replaced by:

{
  "quant_method": "nvfp4_csf",
  "format_version": 1,
  "checkpoint_root": "/path/to/this/checkpoint",
  "source_quantization_config": { "...": "metadata/config.json quantization_config" }
}

The weights are read from checkpoint_root; the serving directory holds only metadata.

Verify or restore

PYTHONPATH=/path/to/trellis-quant python3 -m trellis_quant.lossless_scale_checkpoint verify \
  --checkpoint /path/to/this/checkpoint --workers 16
PYTHONPATH=/path/to/trellis-quant python3 -m trellis_quant.lossless_scale_checkpoint restore \
  --checkpoint /path/to/this/checkpoint --destination /path/to/fresh/dir --workers 16

verify rebuilds every original shard and compares SHA-256 values. restore writes the original shards and metadata files into a fresh directory, checking every hash before a file is published. The result is an ordinary copy of the source checkpoint.

Upstream license

GLM-5.3-Flash (zai-org/GLM-5.3-Flash-BF16) is licensed by Z.AI under the MIT License. Its license text is in LICENSES/MIT.txt, metadata/LICENSE keeps the source checkpoint's copy unchanged, and NOTICE names the upstream materials. This container is licensed under the Local Inference Lab License, Version 1.0 (LICENSE); see License and attribution below.

License and attribution

GLM-5.3-Flash-NVFP4-CSF-QAD is licensed under the Local Inference Lab License, Version 1.0, which reproduces the terms and conditions of the Apache License, Version 2.0, and adds conditions that restrict them. It is not the Apache License, and these files are not open source. Copyright (c) 2026 Local Inference Lab, Inc., a non-profit organization, 311 West Main Street, Grayson, Kentucky 41143. Revisions published up to and including revision 7714f3ac972e2b33d35651938771744c8d192f3a were released under the MIT License, and copies of those revisions remain under it. The Local Inference Lab License, Version 1.0 applies to later revisions.

• No reuploads. Do not upload, mirror, or redistribute these files, or any Substantially Similar Copy of them (including renamed, re-sharded, re-packaged, metadata-stripped, converted, or dequantized copies). Link to https://huggingface.co/local-inference-lab/GLM-5.3-Flash-NVFP4-CSF-QAD instead.
• Attribution at the top. Every README, model card, or other landing page for a project, model, dataset, application, service, or distribution that contains, is derived from, or runs GLM-5.3-Flash-NVFP4-CSF-QAD must begin with this Attribution Notice as its first paragraph (a single title line may come before it):

This model is based on GLM-5.3-Flash-NVFP4-CSF-QAD by Local Inference Lab, Inc., a non-profit organization, available at https://huggingface.co/local-inference-lab/GLM-5.3-Flash-NVFP4-CSF-QAD. GLM-5.3-Flash-NVFP4-CSF-QAD is licensed under the Local Inference Lab License, Version 1.0.

Plain-text form:

This model is based on GLM-5.3-Flash-NVFP4-CSF-QAD by Local Inference Lab, Inc., a non-profit organization, available at https://huggingface.co/local-inference-lab/GLM-5.3-Flash-NVFP4-CSF-QAD. GLM-5.3-Flash-NVFP4-CSF-QAD is licensed under the Local Inference Lab License, Version 1.0.

• Keep the marks. Do not remove the license metadata, the Identifying Marks ("Ні пуху, ні пера", LIL-CANARY-6754-8141-80A9-2132), or the copyright notices embedded in these files.
• Breach. A breach of the no-reupload or attribution terms ends the license immediately (Section 5.1), and Local Inference Lab, Inc. may ask hosting services to remove the material (Section 5.2).

File integrity: SHA256SUMS and lil-manifest.json list the SHA-256 of every file.