granite-embedding-278m-multilingual
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
Weight files by format
Facthory’s checks
Safetensors or GGUF files beside pickle-based ones.
The scan has not finished.
The card declares its licence.
The model card is not public.
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
0.9 GB
Weights: 0.6 GB
KV cache: 0.3 GB
Runtime: 0.1 GB
| GPU | Memory | GPUs needed | Per sequence | All sequences |
|---|---|---|---|---|
| NVIDIA L4 | 24 GB | 1 × | 210 tokens/s | 210 tokens/s |
| NVIDIA L40S | 48 GB | 1 × | 604 tokens/s | 604 tokens/s |
| NVIDIA RTX 6000 Ada | 48 GB | 1 × | 671 tokens/s | 671 tokens/s |
| NVIDIA RTX PRO 6000 Blackwell | 96 GB | 1 × | 1,253 tokens/s | 1,253 tokens/s |
| NVIDIA A100 80GB SXM | 80 GB | 1 × | 1,426 tokens/s | 1,426 tokens/s |
| NVIDIA H100 SXM | 80 GB | 1 × | 2,342 tokens/s | 2,342 tokens/s |
| NVIDIA H200 SXM | 141 GB | 1 × | 3,356 tokens/s | 3,356 tokens/s |
| AMD Instinct MI300X | 192 GB | 1 × | 3,706 tokens/s | 3,706 tokens/s |
| AMD Instinct MI325X | 256 GB | 1 × | 4,195 tokens/s | 4,195 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
Uses
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
As the model card publishes them, with the source the card names. Facthory has not run them; results are self-reported unless the hub verified them.
| Benchmark | Metric | Result | Source | Counts toward |
|---|---|---|---|---|
| MTEB AmazonCounterfactualClassification (en) en · test Not counted: not on our list | accuracy | 71.81 | Model card | Not counted: not on our list |
| MTEB AmazonCounterfactualClassification (en) en · test Not counted: not on our list | ap | 34.05 | Model card | Not counted: not on our list |
| MTEB AmazonCounterfactualClassification (en) en · test Not counted: not on our list | ap_weighted | 34.05 | Model card | Not counted: not on our list |
| MTEB AmazonCounterfactualClassification (en) en · test Not counted: not on our list | f1 |
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: apache-2.0
- Access: Weights download without approval
- Parameters: 278M
General-purpose AI model (Article 3(63))
Not indicated. Its task (sentence-similarity) generates no text, audio, images or video, which the Commission’s indicative criterion asks for.
Articles 51 to 55, the obligations for general-purpose AI models, do not bind its provider.
Facthory’s EU AI Act score appears once a person has reviewed these checks. The articles we score against
