Giga-Embeddings-instruct
- Base Decoder-only LLM: GigaChat-3b - Pooling Type: Latent-Attention - Embedding Dimension: 2048
Params
3.5 B
Context
—
Downloads 30d
696 K
Likes
119
Download history
daily snapshots · 29 days698 K413 K
Aug 23Sep 1Sep 11Sep 20
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | f32 | 13.8 GB | 16.2 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Architecture
- GigarEmbedModel
- Parameters
- 3.5 B
- Tensor type
- F32
- Licence
- mit
- First seen on the Hub
- 2024-12-11
- Training datasets
- undisclosed
- Added to our catalog
- 2026-08-23
Compare with any feature-extraction model