Z.ai · Text
GLM models: Versions, specs, GPU requirements & hosting
Z.ai GLM combines large agentic language models with independent fast and vision tracks; GLM-5.3 is the current verified general generation and uses the GLM-5.2 base architecture with newer post-training.
Overview and history
GLM is an official Z.ai model family represented here through independently verified release, checkpoint, license, runtime and hardware evidence. Z.ai GLM combines large agentic language models with independent fast and vision tracks; GLM-5.3 is the current verified general generation and uses the GLM-5.2 base architecture with newer post-training. Current public releases are grouped by the General, Fast, Vision tracks so sibling sizes and specialist branches are not presented as false chronological generations.
FusionPointAI currently tracks 22 certified public GLM releases. The catalogue preserves release dates and evaluates Current, Recent, Previous and Legacy status within each model track rather than by database insertion order.
Agentic reasoning
Long-context deployment
Separate vision and fast tracks
Architecture and model range
The verified public range spans 10.29B to 744B total parameters and context windows up to 1,048,576 tokens. Each release states whether it is dense or mixture-of-experts and records active parameters separately when the official source publishes them.
Public releases22
Model tracks3
Current generationGLM-5.3-Flash
Last verified2026-09-04T00:00:00.000000Z
Generations, tracks and variants
General
GLM-4.5
Recent generation 2 sibling variantsglm-4-7
Recent generation 3 sibling variantsGLM-4.7-FP8
The manufacturer has not published this information. parameters · N/A / Not directly comparable context
Quantization
GLM-4.7
355.0B parameters · 202,752 context
Flagship · MoE
Glm4MoeForCausalLM
GLM-4.7-NVFP4
The manufacturer has not published this information. parameters · N/A / Not directly comparable context
Quantization
glm-5-1
Recent generation 3 sibling variantsGLM-5.1-FP8
The manufacturer has not published this information. parameters · N/A / Not directly comparable context
Quantization
GLM-5.1
744.0B parameters · 202,752 context
MoE
GlmMoeDsaForCausalLM
GLM-5.1-NVFP4
The manufacturer has not published this information. parameters · N/A / Not directly comparable context
Quantization
glm-5
Recent generation 3 sibling variantsGLM-5-FP8
The manufacturer has not published this information. parameters · N/A / Not directly comparable context
Quantization
GLM-5
744.0B parameters · 202,752 context
MoE
GlmMoeDsaForCausalLM
GLM-5-NVFP4
The manufacturer has not published this information. parameters · N/A / Not directly comparable context
Fine-tune
glm-5-2
Recent generation 3 sibling variantsGLM-5.2-FP8
The manufacturer has not published this information. parameters · N/A / Not directly comparable context
Quantization
GLM-5.2-NVFP4
The manufacturer has not published this information. parameters · N/A / Not directly comparable context
Quantization
GLM-5.2
744.0B parameters · 1,048,576 context
Flagship · MoE
GlmMoeDsaForCausalLM
Fast
GLM-4.7
Legacy generationGLM-5.3
Current generationVision
GLM-4.5V
Recent generationglm-4-6
Recent generationGLM-4.6V
Current generation 2 sibling variantsDeployment ecosystem
Choose a specific GLM release and certified checkpoint before sizing hardware. FusionPointAI rejects unknown runtime configurations, calculates resident memory from total model weights, then distinguishes globally compatible GPUs from currently rentable inventory.
Validate the exact checkpoint license, runtime version, precision kernel, context length, concurrency and multi-GPU topology. Active MoE parameters affect compute, but resident model memory continues to use total stored weights.
Common use cases
Agent platforms
Reasoning APIs
Enterprise knowledge systems
License overview
Licenses are certified per release, not inferred from the provider. Review the release page before commercial deployment because terms can differ between generations and variants.
Commercial-use status is a source-backed catalogue classification, not legal advice. Follow the linked official license and attribution requirements.
Release timeline
zai/glm/glm-47-fp8 @ a3479f6a504e58af9cdb79427a7229c0f474c5e5161cc3282c950d6f415bd1bc
zai/glm/glm-46v-fp8 @ b2c78c825dec3b071cca160b8a0045d6cb8301c51406934bd2add1e56686a9df
zai/glm/glm-51-fp8 @ 2ce6101810d18ca6f636fc1ebc27dc428ac3105d072d18965a78960c730ae795
zai/glm/glm-5-fp8 @ 7bd431e872c5e2224c9a8daa4a7a45eae470696f93952d86eba2157be3ab6e75
zai/glm/glm-52-fp8 @ aca03db797117fcc7b8e12088d5641f1191981fd8543d244f1c15f3c3434e647
zai/glm/glm-47-nvfp4 @ 3a7e6eea05b153333007bc6dc850143b86b448a37662f5798635134d2b9587fd
zai/glm/glm-4-5 @ c6d66eec6dc6a38e2df9beb8f766aeef48d3d4d0b2fefe3f53c2d2820f56fdb3
zai/glm/glm-4-6v @ 4620f5ad6d0915735654f157ecb5d0183a93b9b0a7a4fece25ab7f3983158f50
zai/glm/glm-4-6v-flash @ 01889dafc2091bf309d7e0a6671c37c0cfe0602819c9dd67c4a2ceac055056e6
zai/glm/glm-4-7 @ cbfa55ee9f683a6e1eb532dd9a4a0bae9630c4db9d3141caf1b55601614184f1
zai/glm/glm-4-7-flash @ dcf13b0a7be7e03cf02d6537df02dac6875b209cb9b1f81c247c89652729b9ca
zai/glm/glm-5-3 @ f3d68daa9a0dd3fbe261b5b84df3871adcfc4a189125bb4aff6d7cd953ebd3ed
zai/glm/glm-5-3-flash @ 925c6647cbf1c9ad3acc32541ac622ff5c77ca509cb2dd2ad949e53edeceeaac
zai/glm/glm-5-2 @ cd87f2e073a9a24b8b0c54fe4919d5c80384a2529266dc8bb613833558d1a06f
zai/glm/glm-51-nvfp4 @ 2ab4f89eef4b0a59e264783cf244ec837c4970e480818bf36bd1bc4f32b9b65d
zai/glm/glm-5-nvfp4 @ 3e917b86b2fbb0af0f090ec75dd3440759dad404281e035f32202d5376c329a1
zai/glm/glm-5-1 @ 78ba95751d128a92712bd58f69c1f450c2eee3fc4481b847ccabdad722d79de8
zai/glm/glm-5 @ 76642823d81bc3e3453865302cef97b4105d1910c06e8c23e3fbbbf0697c0091
zai/glm/glm-52-nvfp4 @ 1f864833431fe13229ae1af93f948286242e5314435e7a61cbe9ad32a4e2c185
zai/glm/glm-4-5v @ dafa0d69af66fde66f377179e23238976225223b0d31af2f562f1d50cda62add
zai/glm/glm-53 @ c11d7dae54d007db7e07d584775d2cedfdde5f0df2e4f47c6d8da89197e271d2
ZhipuAI/GLM-5.3 @ 2026-08-31T22:48:39Z
ZhipuAI/GLM-5.3-Flash @ 2026-08-31T12:52:00Z
ZhipuAI/GLM-4.6V @ 2026-01-20T02:51:15Z
Frequently asked questions
Which GLM release is current?
Current releases are GLM-4.6V, GLM-4.6V Flash, GLM-5.3-Flash, GLM-5.3, GLM-5.3, evaluated within their respective tracks.
Can GLM be self-hosted?
Only releases with a verified official checkpoint and supported runtime configuration are presented as deployable.
Which GPU should run GLM?
GPU selection depends on the exact variant, checkpoint precision, context length and concurrency; use the release hardware recommendations rather than the family name alone.
Official references
- huggingface.co
- huggingface.co
- huggingface.co
- huggingface.co
- huggingface.co
- huggingface.co
- huggingface.co
- huggingface.co
- huggingface.co
- huggingface.co
- huggingface.co
- modelscope.cn
- huggingface.co
- huggingface.co
- huggingface.co
- huggingface.co
- huggingface.co
- huggingface.co
- huggingface.co
- huggingface.co
- huggingface.co
- huggingface.co
Last verified: 2026-09-04