SAVRN Model Hub · Comparisons
bert-base-chinese vs distilbert-base-uncased
Bert-base-chinese has 103M parameters and distilbert-base-uncased has 67M parameters; both are released under Apache License 2.0; at 16-bit, bert-base-chinese needs about 0.2 GB (1x MI300X from $1.85 an hour) and distilbert-base-uncased about 0.2 GB (1x MI300X from $1.85 an hour).
| Field | bert-base-chinese google-bert/bert-base-chinese | distilbert-base-uncased distilbert/distilbert-base-uncased |
|---|---|---|
| Publisher | BERT community | DistilBERT community |
| Task | Fill mask | Fill mask |
| Modality | Text | Text |
| Parameters, as reported | 103M parameters | 67M parameters |
| Architecture | BertForMaskedLM | DistilBertForMaskedLM |
| Library | transformers | transformers |
| Context length | 512 tokens | 512 tokens |
| Repository size | 1.7 GB | 1.5 GB |
| Artifact formats | safetensors, pytorch, jax, tf | safetensors, pytorch, jax, rust, tf |
| License | apache-2.0 | apache-2.0 |
| Access | Open weights, no gate | Open weights, no gate |
| Memory at 16-bit (weights and margin) | 0.2 GB | 0.2 GB |
| Cheapest GPUs at 16-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Memory at 4-bit (weights and margin) | 0.1 GB | 0 GB |
| Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Revision viewed | 8f23c25b06e1 | 12040accade4 |
| Downloads reported by the hub | 970.9k | 7.5M |
| Last observed | 2026-09-18 | 2026-09-19 |
An evaluation row appears only where at least two of these models report the same benchmark with the same stated configuration, metric, unit and setup. Different evaluators stay named in each cell. Values are shown as reported: no unit conversion, no ranking.
SAVRN's Notes on bert-base-chinese
We still see this encoder in production more than most people would guess: 970,946 downloads a month for a 103 million parameter masked language model published March 2, 2022. Fill mask is the task, the piece under a Chinese text classifier or embedding job, not a chat model. Memory is trivial, 0.2 GB at 16-bit and 0.1 GB at 8-bit or 4-bit. The cheapest Index host is an MI300X with 192 GB at $1.85 an hour, the wrong size for this alone; pack it with other services.
Apache 2.0 permits commercial use, modification and redistribution, with notices kept, significant changes stated and a patent grant included. Access is open, and the weights ship in safetensors, pytorch, jax and tf, so the serving stack is your choice. The limit to check is context: 512 tokens over a 21,128 entry vocabulary, so long documents get chunked before they reach the model.
SAVRN's Notes on distilbert-base-uncased
At 4-bit the memory line rounds to zero. That settles the hardware question for distilbert-base-uncased: 67M parameters, 0.2 GB needed at 16-bit, 0.1 GB at 8-bit, so the cheapest listed setup, one MI300X with 192 GB at $1.85 an hour, is far more card than the job. The task is fill mask, uncased, so english and English read the same, distilled from BERT base as teacher on bookcorpus and wikipedia with no human labels.
Apache 2.0 lets you ship it commercially, modify it and redistribute it, provided the license, copyright notices and any NOTICE file stay attached and significant changes are stated. Context is 512 tokens, which caps the span you mask in one pass. The 1.5 GB download across 12 files carries safetensors, PyTorch, JAX, Rust and TensorFlow; pick one. Check that a masked-language-model head, which is what DistilBertForMaskedLM ships, matches your pipeline.
Questions
Which is larger, bert-base-chinese or distilbert-base-uncased?
bert-base-chinese (103M parameters) is larger than distilbert-base-uncased (67M parameters), by the parameter counts their publishers report.
Which is cheaper to run, bert-base-chinese or distilbert-base-uncased?
At 4-bit, bert-base-chinese fits on 1x MI300X from $1.85 an hour and distilbert-base-uncased on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use bert-base-chinese commercially?
Yes. bert-base-chinese is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
Can I use distilbert-base-uncased commercially?
Yes. distilbert-base-uncased is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.