Open-weight model · Image and text to text
REX-Gemma-4-26B-A4B-Bio-F3
by AI45Research AI45Research/REX-Gemma-4-26B-A4B-Bio-F3
REX-Gemma-4-26B-A4B-Bio-F3 is an open-weight model for image and text to text from AI45Research, released under Apache License 2.0. It has 28B parameters. At 16-bit it needs about 67.1 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
Parameters28B
Context—
Weights—
Licenseapache-2.0
AccessOpen weights
Monthly Downloads—
Runs On
What it takes to serve REX-Gemma-4-26B-A4B-Bio-F3 (28B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 55.9 GB | 67.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 28.0 GB | 33.6 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 14.0 GB | 16.8 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Oct 20, 2026.
REX-Gemma-4-26B-A4B-Bio-F3 on every accelerator the SAVRN Index prices, at every precision
Model Card
Identity and Version
- Repository
- AI45Research/REX-Gemma-4-26B-A4B-Bio-F3
- Publisher
- AI45Research
- Task
- Image and text to text
- Modality
- Image and text
- Library
- transformers
- Parameters
- 28B parameters
- Languages
- rex
- Revision
- 58bee57ef87f8411c4b8d82e278c76f3c4185208
- First published
- 2026-10-16
- Last updated
- 2026-10-20
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
Download from AI45Research
Released by AI45Research through its official repository on Hugging Face. Read the license.
Built From
- Derived from google/gemma-4-26B-A4B
- Described by arXiv:2610.25791
Memory Requirements
| Precision | Weights in memory |
|---|---|
| 16-bit | 55.9 GB |
| 8-bit | 28.0 GB |
| 4-bit | 14.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About REX-Gemma-4-26B-A4B-Bio-F3
How much GPU memory does REX-Gemma-4-26B-A4B-Bio-F3 need?
About 67.1 GB at 16-bit and 16.8 GB at 4-bit: the weights (28B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run REX-Gemma-4-26B-A4B-Bio-F3 on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use REX-Gemma-4-26B-A4B-Bio-F3 commercially?
Yes. REX-Gemma-4-26B-A4B-Bio-F3 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.
Similar Models
Qwen3.8-27B in MXFP4 for one AMD Radeon AI PRO R9700 (32 GB). Needs GGZ14's vLLM-Radiance fork plus our patches (quantmethod: paroquantmxfp4; stock vLLM and transformers can't load it). Setup: github.com/mtstanfield/vllm-mxfp4, branch r9700-tp1, R9700-HANDOFF.md. MTP speculative decoding with 4 draft tokens. Full BetterBench report and setup: R9700-HANDOFF.md on the branch. pairwise rotations per 128-channel group, retrained for the MXFP4 grid from z-lab's int4 rotations. - GPTQ onto the MXFP4 grid in the rotated basis, with per-block scale search. - lmhead fp8 per-channel, embedtokens fp8 per-row, MTP head fp8. extras/qwen38-paro-v2-mtp-gptq-a05.pt is the MTP head requantized to MXFP4 with…
Following the February release of the Qwen3.5 series, we're pleased to share the first open-weight variant of Qwen3.6. Built on direct feedback from the community, Qwen3.6 prioritizes stability and real-world utility, offering developers a more intuitive, responsive, and genuinely productive coding experience. This release delivers substantial upgrades, particularly in For more details, please refer to our blog post Qwen3.6-27B. Empty cells (--) indicate scores not yet available or not applicable. For streamlined integration, we recommend using Qwen3.6 via APIs. Below is a guide to use Qwen3.6 via OpenAI-compatible API. Qwen3.6 can be served via APIs with popular inference frameworks. In…
Following the widespread community adoption of the Qwen3.5 and Qwen3.6 series, we are pleased to introduce Qwen3.8, the most capable generation in the Qwen open-model family to date. Built on the architectural foundation of Qwen3.5, Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks. Qwen3.8-27B brings these advances to a compact, deployment-friendly dense model: a native vision-language model that understands images and videos, with flexible thinking control, designed to carry complex, multi-step tasks through to completion with greater reliability. For streamlined integration, we recommend using Qwen3.8 via APIs. Qwen3.8 can be…
Following the widespread community adoption of the Qwen3.5 and Qwen3.6 series, we are pleased to introduce Qwen3.8, the most capable generation in the Qwen open-model family to date. Built on the architectural foundation of Qwen3.5, Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks. Qwen3.8-27B brings these advances to a compact, deployment-friendly dense model: a native vision-language model that understands images and videos, with flexible thinking control, designed to carry complex, multi-step tasks through to completion with greater reliability. For streamlined integration, we recommend using Qwen3.8 via APIs. Qwen3.8 can be…
Following the February release of the Qwen3.5 series, we're pleased to share the first open-weight variant of Qwen3.6. Built on direct feedback from the community, Qwen3.6 prioritizes stability and real-world utility, offering developers a more intuitive, responsive, and genuinely productive coding experience. This release delivers substantial upgrades, particularly in For more details, please refer to our blog post Qwen3.6-27B. Empty cells (--) indicate scores not yet available or not applicable. For streamlined integration, we recommend using Qwen3.6 via APIs. Below is a guide to use Qwen3.6 via OpenAI-compatible API. Qwen3.6 can be served via APIs with popular inference frameworks. In…