GLM-5.1-MXFP4
Support summary
GLM-5.1-MXFP4 is a checkpoint. Official recipes or cookbooks cover vLLM and SGLang, without pinning a stable release.
- Documented hardware
- AMD / ROCm
- Documented quantization
- MXFP4
- Documented features
- Prefix caching, Reasoning parsers, Speculative decoding, Tensor parallelism, and Tool calling
Hardware, quantization and features count only statements about this checkpoint; engine-wide capabilities are listed with each release.
Model notes and sources
- vllm · models/zai-org/GLM-5.1.yaml
- sglang · docs/src/snippets/autoregressive/glm-51-deployment.jsx
- sglang · docs/cookbook/autoregressive/GLM/GLM-5.1.mdx · 2 indexed revisions, dc2843801d02f9130feff04635803353561eb604 to dc2843801d02f9130feff04635803353561eb604
- Reviewed
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-5.1.yamlReviewed | No supported release indexed | |
Features, dependencies and evidence for vLLM 0.28.0 | ||||
| SGLang | Version not pinnedRecipe / cookbook | Documented recipeSource 1: sglang · docs/cookbook/autoregressive/GLM/GLM-5.1.mdxSource 2: sglang · docs/src/snippets/autoregressive/glm-51-deployment.jsxReviewed | 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 | ||||