GLM-5.3-Flash-BF16
Support summary
GLM-5.3-Flash-BF16 is a checkpoint published by Z.ai, built on the Glm5NextForConditionalGeneration architecture. Official recipes or cookbooks cover vLLM, without pinning a stable release.
- Documented quantization
- BF16
- Configured context
- 1,048,576 tokens
- License
- mit
Hardware, quantization and features count only statements about this checkpoint; engine-wide capabilities are listed with each release.
Hugging Face model card
- Publisher
- Z.ai
- Task
- image text to text
- License
- mit
- Library
- transformers
- Architecture
- Glm5NextForConditionalGeneration
- Weight tensor elements
- 321.3B
- Tensor types
- F32, BF16
- Configured context
- 1,048,576 tokens
- Languages
- en, zh
- Weight access
- Public
- Repository created
- 2026-08-25
Publisher deployment guidance
- vLLMVersion unspecified
The publisher links a deployment recipe without specifying a stable engine version.
Source: zai-org/GLM-5.3-Flash-BF16 · publisher model cardReviewed - SGLangVersion unspecified
The publisher links a deployment recipe without specifying a stable engine version.
Source: zai-org/GLM-5.3-Flash-BF16 · publisher model cardReviewed
Engine support
3 engines
| Engine | Release | Checkpoint support | Evidence scope | Last known supported |
|---|---|---|---|---|
| vLLM | Version not pinnedRecipe / cookbook | Documented recipeSource: vllm · models/zai-org/GLM-5.3-Flash.yamlReviewed | No supported release indexed | |
Features, dependencies and evidence for vLLM 0.28.0 | ||||
| SGLang | 0.5.19Newest indexed | No matching evidence curated | No supported release indexed | |
Features, dependencies and evidence for SGLang 0.5.19 | ||||
| TensorRT-LLM | 1.2.1Newest indexed | No matching evidence curated | No supported release indexed | |
Features, dependencies and evidence for TensorRT-LLM 1.2.1 | ||||