SAVRN
Search Contact SAVRN

SAVRN Model Hub · Comparisons

Qwen3-4B vs xflux_text_encoders

Qwen3-4B has 4B parameters and xflux_text_encoders has 4.8B parameters; both are released under Apache License 2.0; at 16-bit, Qwen3-4B needs about 9.7 GB (1x MI300X from $1.85 an hour) and xflux_text_encoders about 11.4 GB (1x MI300X from $1.85 an hour).

Published metadata for 2 models, each read from its own repository.
Field Qwen3-4B
Qwen/Qwen3-4B
xflux_text_encoders
XLabs-AI/xflux_text_encoders
Publisher Qwen XLabs AI
Task Text generation Text generation
Modality Text Text
Parameters, as reported 4B parameters 4.8B parameters
Architecture Qwen3ForCausalLM T5EncoderModel
Library transformers transformers
Context length 40,960 tokens Not stated
Repository size 8.1 GB 9.5 GB
Artifact formats safetensors safetensors, pytorch
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 11.4 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 2.9 GB
Cheapest GPUs at 4-bit, per hour 1x MI300X, $1.85 1x MI300X, $1.85
Revision viewed 1cfa9a720891 5ce032c6b9bf
Downloads reported by the hub 6.9M 320.5k
Last observed 2026-09-21 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 Qwen3-4B

Memory is not the constraint with Qwen3-4B. The 16-bit weights are 8.0 GB and need 9.7 GB to serve, 8-bit needs 4.8 GB and 4-bit 2.4 GB, so on the cheapest Index setup, one MI300X with 192 GB at $1.85 an hour, the card sits mostly empty and the decision is how many copies to run. It is text only, switches between a thinking mode and a plain dialogue mode, and carries a 40,960-token context.

Apache 2.0 lets you fine-tune it, ship it in a product and charge for it, provided the license and notices travel with it and you state what you changed. Before you commit, look at the lineage and the price sheet: it is derived from Qwen3-4B-Base, so decide whether you want this release or the base for post-training, and the page lists no Index host prices, so there is nothing per token to compare with.

Questions

Which is larger, Qwen3-4B or xflux_text_encoders?

xflux_text_encoders (4.8B parameters) is larger than Qwen3-4B (4B parameters), by the parameter counts their publishers report.

Which is cheaper to run, Qwen3-4B or xflux_text_encoders?

At 4-bit, Qwen3-4B fits on 1x MI300X from $1.85 an hour and xflux_text_encoders on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.

Can I use Qwen3-4B commercially?

Yes. Qwen3-4B 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 xflux_text_encoders commercially?

Yes. xflux_text_encoders 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