Model
GLM-5.3-Flash
Recorded as suitable for chat, rag, coding, reasoning, zh, multilingual, vision, agentic, long context.
- Source
- Model registry API
- Verified
- 19 Sep 2026
- Confidence
- High
01What this is
- Author
- zai-org
- Family
- GLM-5.3
- Task
- vision-language
- Hugging Face
- zai-org/GLM-5.3-Flash
- OpenRouter
- z-ai/glm-5.3-flash
- Also known as
- GLM-5.3-Flash, GLM 5.3 Flash, z.ai glm flash
02Registry facts
- LicenceFACT
mit
- FreshRetrieved 19 Sep 2026
- ParametersFACT
321.3B
- FreshRetrieved 19 Sep 2026
- Context lengthFACT
not returned by the registry
- Evidence not verified
- Downloads (30 days)FACT
2,905,932
- FreshRetrieved 19 Sep 2026
- LikesFACT
2,467
- FreshRetrieved 19 Sep 2026
- GatedFACT
no
- FreshRetrieved 19 Sep 2026
Model
- downloadsFACT
2905932
- Verification may be outdatedRetrieved 19 Sep 2026
- gatedFACT
false
- Verification may be outdatedRetrieved 19 Sep 2026
- hosted context length · RelaceFACT
1048576
- Verification may be outdatedRetrieved 19 Sep 2026
- hosted context length · InferenceNetFACT
1048576
- Verification may be outdatedRetrieved 19 Sep 2026
- hosted context length · DeepInfraFACT
1048576
- Verification may be outdatedRetrieved 19 Sep 2026
- likesFACT
2467
- Verification may be outdatedRetrieved 19 Sep 2026
- model licenseFACT
mit
- Verification may be outdatedRetrieved 19 Sep 2026
- parameter countFACT
321323031390
- Verification may be outdatedRetrieved 19 Sep 2026
Pricing
- hosted price completion per m · RelaceFACT
0.3000
- AgeingRetrieved 19 Sep 2026
- hosted price completion per m · InferenceNetFACT
0.2800
- AgeingRetrieved 19 Sep 2026
- hosted price completion per m · DeepInfraFACT
0.2500
- AgeingRetrieved 19 Sep 2026
- hosted price prompt per m · RelaceFACT
0.0900
- AgeingRetrieved 19 Sep 2026
- hosted price prompt per m · InferenceNetFACT
0.0900
- AgeingRetrieved 19 Sep 2026
- hosted price prompt per m · DeepInfraFACT
0.0750
- AgeingRetrieved 19 Sep 2026
Other
- available on platform · vendorFACT
vendor
- AgeingRetrieved 19 Sep 2026
- last modifiedFACT
2026-09-07T12:13:47.000Z
- Verification may be outdatedRetrieved 19 Sep 2026
- libraryFACT
transformers
- AgeingRetrieved 19 Sep 2026
03VRAM by quantisation
Peak VRAM for serving this model, computed by lib/deployment/hardware.ts from weights + KV cache + 15% runtime overhead. Inputs: 321.3B parameters, 8,192 tokens of context (assumed — none fetched yet), 4 concurrent requests (assumed).
| Quantisation | Weights | Total |
|---|---|---|
| bf16bf16 is two bytes per weight, the same arithmetic as fp16. | 642.65 GB | 756.33 GB |
| fp8 | 321.32 GB | 386.81 GB |
| int4 | 160.66 GB | 202.05 GB |
What this estimate assumes
- Weights: 321.3B parameters × 2 bytes per parameter (fp16) = 642.65 GB.
- No model configuration was supplied, so the KV cache uses the size heuristic for this band: 0.459 MB per token, from extrapolated above 90B — no configuration was fetched for this band.
- KV cache: 0.459 MB per token × 8,192 tokens of context × 4 concurrent requests = 15.03 GB, sized for every user holding a full context at once.
- Overhead: 15% of weights plus KV cache for the runtime, activations and memory fragmentation = 98.65 GB.
- GB means 10⁹ bytes, matching how GPU memory is advertised.
- KV cache held at fp16 (2 bytes per element); quantising weights does not by itself quantise the cache.
- Peak figure, not average: prefix caching and paged attention usually keep real usage lower, while speculative decoding, CUDA graphs and a second resident model push it higher.
- "Concurrent" counts requests generated at the same instant, not people: 4 simultaneous requests is the worst case this estimate is built on — measure yours before buying.
04Hardware profiles
No hardware profile was sized for this answer.
05Hosted providers
- Prompt (per million tokens, USD)FACT
0.075
Source: openrouter
- FreshRetrieved 19 Sep 2026
- Completion (per million tokens, USD)FACT
0.25
- FreshRetrieved 19 Sep 2026
| Provider | Context |
|---|---|
| DeepInfra | 1,048,576 |
| InferenceNet | 1,048,576 |
| Relace | 1,048,576 |
| Wafer | 1,048,576 |
| GMICloud | 1,048,576 |
| Novita | 1,048,576 |
06Deployment stacks
No published deployment stack names this model yet.
07Evidence
- 01Tier 2official vendor legal documentationVendor legal and technical documentation
GLM-5.3-Flash/FlashX - Overview - Z.AI DEVELOPER DOCUMENT
https://docs.z.ai/guides/vlm/glm-5.3-flash
AgeingRetrieved 19 Sep 2026sha256:e8e2912565801 record
- 02–10Tier 4official repository / model cardOpenRouter
OpenRouter endpoints — z-ai/glm-5.3-flash
https://openrouter.ai/api/v1/models/z-ai/glm-5.3-flash/endpoints
AgeingRetrieved 19 Sep 2026sha256:31676d7e15b09 records · · · · · · · ·
- 11–17Tier 4official repository / model cardHugging Face Hub
Hugging Face model card data — zai-org/GLM-5.3-Flash
https://huggingface.co/api/models/zai-org/GLM-5.3-Flash
Verification may be outdatedRetrieved 19 Sep 2026sha256:62536586ee987 records · · · · · ·
Improve this page
Sign in to contribute
From the field
0 deployments · 0 questions
Nobody has reported deploying this here yet, and no question has been opened against this page. Both appear once a reviewer accepts them.