Qwen3-Embedding-8B vs e5-mistral-7b-instruct-bnb-4bit
Specs, VRAM requirements and download trends — updated 21 September 2026.
gabor-hosu · B
Params
7.3 B
Context
32,768
30d
1.0 M
mit · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3-Embedding-8B | e5-mistral-7b-instruct-bnb-4bit |
|---|---|---|
| Parameters | 7.6 B | 7.3 B |
| Architecture | Qwen3ForCausalLM | MistralModel |
| Context length | 40,960 | 32,768 |
| Licence | apache-2.0 | mit |
| Commercial use | Allowed | Allowed |
| Languages | — | 1 |
| Downloads 30d | 2,575,478 | 1,034,344 |
| Downloads all time | 23.7 M | 1.3 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-06-03 | 2026-01-09 |
Download trend
Daily snapshots, last 56 days (28 Jul – 21 Sep)
3.4 M442 K
Qwen3-Embedding-8B
e5-mistral-7b-instruct-bnb-4bit
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
e5-mistral-7b-instruct-bnb-4bit · fp16
5.8 GB / 24 GB
Qwen3-Embedding-8B · fp16
18.3 GB / 24 GB