SAVRN
Search Contact SAVRN

SAVRN Model Hub · Comparisons

Qwen3-Embedding-4B-W4A16-G128 vs Qwen3-Embedding-8B

Qwen3-Embedding-4B-W4A16-G128 has 4.1B parameters and Qwen3-Embedding-8B has 7.6B parameters; both are released under Apache License 2.0; at 16-bit, Qwen3-Embedding-4B-W4A16-G128 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).

Published metadata for 2 models, each read from its own repository.
Field Qwen3-Embedding-4B-W4A16-G128
boboliu/Qwen3-Embedding-4B-W4A16-G128
Qwen3-Embedding-8B
Qwen/Qwen3-Embedding-8B
Publisher Mou Geren Qwen
Task Feature extraction Feature extraction
Modality Text Text
Parameters, as reported 4.1B parameters 7.6B parameters
Architecture Qwen3ForCausalLM Qwen3ForCausalLM
Library sentence-transformers sentence-transformers
Context length 40,960 tokens 40,960 tokens
Repository size 2.7 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 9da6cb71a687 1d8ad4ca9b3d
Downloads reported by the hub 591.4k 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-4B-W4A16-G128

Two relations in the file frame this one: it is a GPTQ quantization of Qwen/Qwen3-Embedding-4B, published by Mou Geren, not Qwen. The calibration set was THUIR/T2Ranking and m-a-p/COIG-CQIA, and the publisher reports about 0.72 percent lost on C-MTEB. The 4-bit row matches the 2.65 GB of safetensors on disk: 2.0 GB of weights and 2.4 GB of working memory. The cheapest Index listing, one MI300X at $1.85 per hour on-demand, leaves nearly the whole card free for the retrieval workload these embeddings feed.

Apache 2.0 permits commercial use, modification and redistribution, with the license and copyright notices kept, significant changes stated, and an express patent grant from contributors. Check that Qwen/Qwen3-Embedding-4B is the model your evaluation ran on, since this derivative was released June 6, 2025; that your documents fit in 40,960 tokens; and that your stack loads it through sentence-transformers.

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-W4A16-G128 or Qwen3-Embedding-8B?

Qwen3-Embedding-8B (7.6B parameters) is larger than Qwen3-Embedding-4B-W4A16-G128 (4.1B parameters), by the parameter counts their publishers report.

Which is cheaper to run, Qwen3-Embedding-4B-W4A16-G128 or Qwen3-Embedding-8B?

At 4-bit, Qwen3-Embedding-4B-W4A16-G128 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-W4A16-G128 commercially?

Yes. Qwen3-Embedding-4B-W4A16-G128 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.

Related Comparisons