available
Weights
Official weights are downloadable.
Inspect this claim’s source ↗Z.ai / FAMILY RECORD
GLM-5.3 Flash: license, size and what is open.
A natively multimodal sparse GLM checkpoint released under MIT terms for long-context agent and coding work.
Sizes and download
320B total / 18B active
- GLM-5.3-Flash
- Total: 320B. Active: 18B. Source ↗
About 328.34 GB of selected documented weights · File listing ↗
Selected artifact: zai-org/GLM-5.3-Flash. Format: Safetensors, FP8. File evidence checked 2026-10-11. Selected artifact license: mit ↗
All 62 checkpoint shards; FP8 with unconverted modules as described by configuration. Selected weight files only; supporting files and runtime memory are separate. Not a smallest-download census or proof of hardware compatibility.
Can my computer run it?
Compatibility, runtime memory and speed are untested by Bright.
Choose your computer and inspect documented candidates →Nine things to check
Source check: . Downloads, when known, carry their own check date.
Checked release: GLM-5.3-Flash
Sources checked 2026-09-19
- GLM-5.3-Flash release
- · Primary source
The profile describes this checkpoint, not every release carrying the family name. Developer documentation is not independent reproduction.
THE MODEL / THE TERMS
Know what you are picking up.
- Parameters
- 320B total / 18B active
- Architecture
- Mixture-of-experts transformer with hybrid sparse and linear attention.
- Modalities
- text · image
- Context
- 1M tokens
- Weights license
- MIT
- Commercial use
- Permitted by the MIT license for this Flash checkpoint; other GLM 5.3 variants have different terms.
- Memory
- No reliable universal minimum is stated; the 320B checkpoint requires distributed or quantized serving.
- Known quantizations
- Runtime-specific community quantizations exist; the canonical release should be checked first
Specifications are developer-reported. Primary release documentation ↗ · All sources and terms
NINE DIMENSIONS / NO OPENNESS SCORE
What is actually available?
Each component has its own evidence. “Not established” means this source review did not verify availability; it is not a claim that nothing exists.
available
Architecture
Configuration and attention design are documented.
Inspect this claim’s source ↗available
Inference code
Official examples and a vLLM recipe are public.
Inspect this claim’s source ↗not established
Training code
Complete training code was not confirmed.
Inspect this claim’s source ↗partial
Training recipe
Core methods are described without a complete reproduction recipe.
Inspect this claim’s source ↗not established
Data information
A sufficiently detailed data mixture was not confirmed.
Inspect this claim’s source ↗not established
Training data
No sufficiently specific public artifact was confirmed in this review.
Inspect this claim’s source ↗partial
Evaluation
Vendor results and evaluation information are published.
Inspect this claim’s source ↗available
Commercial use
The Flash checkpoint is MIT-licensed.
Inspect this claim’s source ↗WHY THIS RELEASE MATTERS
What to explore.
- Long context
- Native multimodality
- Sparse inference
- Permissive checkpoint license
WHAT THE RECORD DOES NOT ESTABLISH
Keep the limits.
- Training data is not disclosed in enough detail
- Large server-class checkpoint
The vLLM recipe corroborates deployability, not vendor capability claims.
FOLLOW THE RECORD
Sources, not superlatives.
- Z.ai GLM-V release note ↗ (repository)
- GLM-5.3-Flash model card ↗ (registry)
- vLLM GLM-5.3-Flash recipe ↗ (repository)
Source check: 2026-09-19. AI-assisted editorial review, with no named external expert or independent hardware validation claimed. Licenses and model cards can change. Review the linked terms for the specific artifact and intended use.
Understand open source vs open weights ↗