GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
webbrain-one
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
webbrain-one
Model Tree
Nanbeige/Nanbeige4.3-33B
Input Modalities
Output Modalities
Supported Functionality
| Model | GSM8K, first 100 test questions, greedy, non-thinking |
|---|---|
| BF16 original | 96.0% |
| NVFP4 (this repo) | 95.0% |
A small sanity check run right after quantization (vLLM 0.32.0, NVIDIA RTX PRO 6000 Blackwell Server Edition). It catches a broken quant; it is not a benchmark.
bash
vllm serve webbrain-one/Nanbeige4.3-33B-NVFP4 \ --enable-auto-tool-choice \ --reasoning-parser qwen3 \ --tool-call-parser qwen3_coder--kv-cache-dtype fp8 --max-model-len 32768 and raise
the context length based on the KV-cache size vLLM reports at startup. The full 512K context needs
far more memory.enable_thinking, preserve_thinking, tool_call_format) and the
recommended sampling settings are the same as the original: temperature 1.0 / top_p 0.95 for agentic
and tool use, 0.6 / 0.95 for reasoning and chat. See the
original card for details and benchmarks.| Scheme | NVFP4, all decoder Linear layers (364 = 52 layers x 7), lm_head ignored |
| Algorithm | round-to-nearest (QuantizationModifier) |
| Calibration | 256 samples, up to 2048 tokens (mean 552), rendered with the model's chat template: mlabonne/open-perfectblend (256) |
| Tools | llm-compressor 0.14.0.1, compressed-tensors 0.19.0, transformers 5.17.0, torch 2.11.0+cu128 |
| Hardware | NVIDIA RTX PRO 6000 Blackwell Server Edition, 3.1 min |
config.json is the original config plus quantization_config; tokenizer and generation files are
unchanged copies of the original.
Apache-2.0, same as the original model by the Nanbeige LLM Lab.