Runtime recipe
8 × H200 SXM
141 GB per GPU
FP8 weights
vLLM model-specific guide
Single-node TP8 path. Long-context limits depend on remaining cache memory; use the guide’s matching parser and MTP settings.
GLM / MoE
GLM-5.3
A post-training release with a changed adoption decision
New to model sizes or GPU memory? Start with weights, parameters and quantization →
GLM-5.3 should be evaluated as a coding-focused update to the GLM-5.2 base, with license and safety-release changes reviewed separately. It is not evidence that every capability gain required a larger pretrained model.
743Breported total parameters
39Bactive parameters per token
1,048,576configured token positions
Approximate 743B total / 39B active, as reported in the model-specific vLLM guide; not an exact tensor inventory.
Evaluate it for
Controlled coding-agent and authorized defensive-security evaluations on a cluster.
Choose another path when
Inheriting GLM-5.2’s MIT metadata without reading the current checkpoint’s custom terms.
Release context
Why this release matters
The card attributes the update to post-training and highlights cyber-defense evaluations. Hosted access and weights did not arrive together; this history matters when reproducing comparisons or dating adoption.
The pinned card dates its launch comparison August 14; the API release notes are dated August 18. Weights were staged later; do not treat August 14 as their upload date.
Release evidence · Announced 2026-08-14 · Follow the GLM timeline →
Deployment starting points
Which hardware, how many, at what precision?
Start with an exact artifact and an engine that supports it. A configuration below is evidence of a documented path; its device count does not promise a particular throughput or concurrency.
Runtime recipe
8 × B200 HGX
180 GB per GPU
FP8 weights + FP8 KV
vLLM model-specific guide
Guide documents a full 1M context configuration. That is not a measured TTFT or concurrent-service guarantee.
755.62 GB of tensor data in the pinned index
This is the index’s reported tensor payload, in decimal GB. It excludes file headers and runtime memory. Mixed precision, conversion and host/device placement determine how much GPU memory the loaded model needs.
Inspect the exact index metadata →Capacity screen: would the weights fit?
This estimates inference memory for a hypothetical uniform precision. It is useful for rejecting an allocation that is too small. It does not establish a working deployment or estimate training memory.
A uniform-precision GPU count would hide this model’s component layout. Approximate 743B total / 39B active, as reported in the model-specific vLLM guide; not an exact tensor inventory. Use the documented artifact and placement path above; no GPU count is inferred here.
Architecture in practice
What the serving engine has to do
Store the history. Read the selected parts.
Fewer bytes read can reduce bandwidth pressure.
That does not prove an equal reduction in stored bytes.
Mechanism schematic based on the pinned model card and configuration. It explains a design principle; it is not a full implementation graph.
Inspect the full checkpoint specifications
| Exact checkpoint | zai-org/GLM-5.3 |
|---|---|
| Text model type | glm_moe_dsa |
| Layers | 78 |
| Hidden width | 6,144 |
| Attention / KV heads | 64 / 64 |
| Head dimension | 192 |
| Routed / selected experts | 256 / 8 |
| Configured positions | 1,048,576 |
| Documented extension | Not recorded for this checkpoint |
| Inputs → output | text → text |
| License metadata | glm-5.3 · custom terms |
Open weights do not imply unrestricted use. Read the applicable license terms linked from the pinned card.
A useful comparison
What else belongs on the shortlist?
The earlier base lineage isolates the update; K2.7-Code provides an independent coding-focused comparison.
16 Jun 2026
GLM-5.2
A million-token setting backed by index sharing
743B reported total · text
12 Jun 2026
Kimi-K2.7-Code
A coding upgrade without a new size class
1,000B reported total · text + image + video
These are editorial comparison candidates. We have not run a matched quality or serving benchmark, so this is not a ranking.
Prepare to explain it
The interview lesson
Explain a controlled post-training comparison, including harness, reasoning budget and license constraints; keep benchmark gains separate from serving speed.
Attention layouts · Quantization · Courses and worked examples
For a deployment evaluation, record exact weights, precision, engine, device count, interconnect, prompt/output lengths and concurrency. Report task success, errors, TTFT, TPOT and useful throughput together.
Sources and citation
Our assessment is editorial judgment based on the linked architecture and deployment evidence. Model facts are publisher-reported or attributed to runtime maintainers; no independent GPU benchmark was run.
AI Infra Interviews, “GLM-5.3: release, architecture and deployment”, checked 2026-09-13. Preserve this date and the exact checkpoint when citing.