SAVRN Model Hub · Comparisons
Qwen3-Embedding-4B vs Qwen3-Embedding-8B
Qwen3-Embedding-4B has 4B parameters and Qwen3-Embedding-8B has 7.6B parameters; both are released under Apache License 2.0; at 16-bit, Qwen3-Embedding-4B needs about 9.7 GB (1x MI300X from $1.85 an hour) and Qwen3-Embedding-8B about 18.2 GB (1x MI300X from $1.85 an hour).
| Field | Qwen3-Embedding-4B Qwen/Qwen3-Embedding-4B | Qwen3-Embedding-8B Qwen/Qwen3-Embedding-8B |
|---|---|---|
| Publisher | Qwen | Qwen |
| Task | Feature extraction | Feature extraction |
| Modality | Text | Text |
| Parameters, as reported | 4B parameters | 7.6B parameters |
| Architecture | Qwen3ForCausalLM | Qwen3ForCausalLM |
| Library | sentence-transformers | sentence-transformers |
| Context length | 40,960 tokens | 40,960 tokens |
| Repository size | 8.1 GB | 15.2 GB |
| Artifact formats | safetensors | safetensors |
| License | apache-2.0 | apache-2.0 |
| Access | Open weights, no gate | Open weights, no gate |
| Memory at 16-bit (weights and margin) | 9.7 GB | 18.2 GB |
| Cheapest GPUs at 16-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Memory at 4-bit (weights and margin) | 2.4 GB | 4.5 GB |
| Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Revision viewed | 5cf2132abc99 | 1d8ad4ca9b3d |
| Downloads reported by the hub | 2.1M | 2.6M |
| Last observed | 2026-09-18 | 2026-09-18 |
An evaluation row appears only where at least two of these models report the same benchmark with the same stated configuration, metric, unit and setup. Different evaluators stay named in each cell. Values are shown as reported: no unit conversion, no ranking.
SAVRN's Notes on Qwen3-Embedding-8B
Eighteen gigabytes decides the hardware here. At 16-bit the weights take 15.1 GB and the model needs 18.2 GB to run, under a tenth of the 192 GB on the single MI300X we list as the cheapest setup at $1.85 an hour. Do not hand that card to one embedding model; at 4-bit it needs 4.5 GB, so run it as a co-tenant beside a generation model. The 40,960-token context is what 7.6 billion parameters buy: a whole filing embedded in one pass.
Apache 2.0 allows commercial use, modification and redistribution; keep the license and copyright notices and any NOTICE file, and state significant changes if you ship a fine-tuned derivative. Confirm your stack loads sentence-transformers, and note the lineage: derived from Qwen3-8B-Base, described in arXiv:2506.05176, with 0.6B and 4B siblings and matching rerankers. No host price per million tokens yet, so budget from the card rate.
Questions
Which is larger, Qwen3-Embedding-4B or Qwen3-Embedding-8B?
Qwen3-Embedding-8B (7.6B parameters) is larger than Qwen3-Embedding-4B (4B parameters), by the parameter counts their publishers report.
Which is cheaper to run, Qwen3-Embedding-4B or Qwen3-Embedding-8B?
At 4-bit, Qwen3-Embedding-4B fits on 1x MI300X from $1.85 an hour and Qwen3-Embedding-8B on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use Qwen3-Embedding-4B commercially?
Yes. Qwen3-Embedding-4B is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
Can I use Qwen3-Embedding-8B commercially?
Yes. Qwen3-Embedding-8B is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.