Fact sheet
Parameters
Context length
Architecture
Shape
Weights stored as
Task
Languages
Built on
Released
Last updated
Downloads (last 30 days)
Licence and access
Licence
Access
Security
Hugging Face security scan
1 file flagged; the most serious is rated error.
USE_POLICY.md: error
Weight files by format
Facthory’s checks
Safetensors or GGUF files beside pickle-based ones.
Files flagged, none of them rated unsafe.
The card declares its licence.
GPU calculator
How much memory this model needs to serve at a quantization, context and number of concurrent sequences, which GPUs hold it, and how fast it can generate. Estimates from the model’s published size and shape, with the assumptions below.
Weights
Context per sequence: 8K tokens
Concurrent sequences: 1
KV cache
Memory
2.7 GB
Weights: 2.5 GB
KV cache: –
Runtime: 0.2 GB
The model’s shape is not published, so the KV cache is not included.
| GPU | Memory | GPUs needed | Per sequence | All sequences |
|---|---|---|---|---|
| NVIDIA L4 | 24 GB | 1 × | 73 tokens/s | 73 tokens/s |
| NVIDIA L40S | 48 GB | 1 × | 210 tokens/s | 210 tokens/s |
| NVIDIA RTX 6000 Ada | 48 GB | 1 × | 233 tokens/s | 233 tokens/s |
| NVIDIA RTX PRO 6000 Blackwell | 96 GB | 1 × | 435 tokens/s | 435 tokens/s |
| NVIDIA A100 80GB SXM | 80 GB | 1 × | 495 tokens/s | 495 tokens/s |
| NVIDIA H100 SXM | 80 GB | 1 × | 813 tokens/s | 813 tokens/s |
| NVIDIA H200 SXM | 141 GB | 1 × | 1,165 tokens/s | 1,165 tokens/s |
| AMD Instinct MI300X | 192 GB | 1 × | 1,287 tokens/s | 1,287 tokens/s |
| AMD Instinct MI325X | 256 GB | 1 × | 1,457 tokens/s | 1,457 tokens/s |
Assumptions
- Runtime memory (activations, buffers) is 10% of weights and KV cache, plus 1 GB per GPU for the framework.
- A GPU is filled to at most 90% of its memory; tensor parallelism uses 1, 2, 4 or 8 GPUs in one server.
- Generation is limited by memory bandwidth at 60% of the vendor’s peak: each step reads the weights once and every sequence’s KV cache. A mixture-of-experts model reads only its active experts, so it runs faster than shown.
- GPU memory and bandwidth are the vendors’ published figures.
Profile
Kind
Lineage
In and out
Written on 11 Nov 2026 by Workers AI (@cf/zai-org/glm-4.7-flash) from the hub’s metadata: a reading of the publisher’s text, not checked by Facthory.
Published benchmarks
The model card publishes no benchmark results.
EU AI Act
What the EU AI Act asks of a general-purpose AI model depends on who places it on the EU market and how. These facts bear on it:
- Licence: llama3.2
- Access: Weights download after the publisher approves the request
- Parameters: 1.2B
General-purpose AI model (Article 3(63))
Not determined. No estimate of its training compute is published, and the Commission’s indicative criterion (10²³ FLOP) needs one. If it is a general-purpose AI model, the obligations below bind its provider.
Systemic risk (Article 51)
Not presumed. No estimate of its training compute is published; without one, or a designation by the Commission under Article 52, Article 55 does not apply.
Open-source exemption (Article 53(2))
Does not apply. Its licence (llama3.2) is not a free and open-source licence, one that lets anyone use, study, change and share the model.
General-Purpose AI Code of Practice
Meta is not on the European Commission’s list of signatories. The Code is voluntary.
What the card and the provider document
The model card is not public.
The model card is not public.
