llama2-embedding-1b-8k
Trained on truncated 8k context length, but infer able to scale up to 32k context length.
Params
947 M
Context
32,768
Downloads 30d
416 K
Likes
3
Download history
tracking started — chart appears after 7 days of snapshots (2 recorded)416 K downloads in the last 30 days
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 | 3.8 GB | 4.8 GB | ✅ Runs comfortably |
| model.safetensors (bf16, full) | bf16 + 32K ctx | 3.8 GB | 5.2 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
- LlamaModelEmbedding
- Parameters
- 947 M
- Tensor type
- F32
- Context length
- 32,768
- Vocabulary
- 32,000
- Layers / heads
- 4 / 32
- First seen on the Hub
- 2023-10-05
- Training datasets
- undisclosed
- Added to our catalog
- 2026-11-09
Compare with any feature-extraction model