SAVRN Model Hub · Comparisons
gemma-4-E2B-it vs Qwen2.5-Omni-3B
Gemma-4-E2B-it has 5.1B parameters and Qwen2.5-Omni-3B has 5.5B parameters; gemma-4-E2B-it is released under Apache License 2.0 and Qwen2.5-Omni-3B under other; at 16-bit, gemma-4-E2B-it needs about 12.3 GB (1x MI300X from $1.85 an hour) and Qwen2.5-Omni-3B about 13.3 GB (1x MI300X from $1.85 an hour).
| Field | gemma-4-E2B-it google/gemma-4-E2B-it | Qwen2.5-Omni-3B Qwen/Qwen2.5-Omni-3B |
|---|---|---|
| Publisher | Qwen | |
| Task | Any to any | Any to any |
| Modality | Multimodal | Multimodal |
| Parameters, as reported | 5.1B parameters | 5.5B parameters |
| Architecture | Gemma4ForConditionalGeneration | Qwen2_5OmniModel |
| Library | transformers | transformers |
| Context length | 131,072 tokens | Not stated |
| Repository size | 10.3 GB | 12.0 GB |
| Artifact formats | safetensors | safetensors |
| License | apache-2.0 | other |
| Access | Open weights, no gate | Open weights, no gate |
| Memory at 16-bit (weights and margin) | 12.3 GB | 13.3 GB |
| Cheapest GPUs at 16-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Memory at 4-bit (weights and margin) | 3.1 GB | 3.3 GB |
| Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Revision viewed | 3e22461f65e8 | f75b40e3da20 |
| Downloads reported by the hub | 3.5M | 324.2k |
| 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.
Other Reported Results
These results are listed for each model on its own, because the conditions needed to compare them are not stated or do not match. Two results that leave a condition blank are not assumed to share it.
gemma-4-E2B-it
| Benchmark | Conditions | Result | Reported by | Revision | Date |
|---|---|---|---|---|---|
| ARTPARK-IISc/Vaani-Benchmark-V1.0 | Task Hindi_WERMetric Hindi_WERComparison conditions not established | 19.4 | Not named Reported by a third party |
Evaluated revision not stated | 2026-06-26 |
| Idavidrein/gpqa | Task diamondMetric diamondComparison conditions not established | 43.4 | Model Card Reported by a third party |
Evaluated revision not stated | 2026-04-02 |
| LiquidAI/ifstruct-v1.0 | Task ifstruct_v1Metric ifstruct_v1Comparison conditions not established | 64.85 | Liquid AI — IFStruct v1.0 blog (gemma-4-E2B-it) Reported by a third party |
Evaluated revision not stated | 2026-06-30 |
| MMMU/MMMU_Pro | Task mmmu_pro_visionMetric mmmu_pro_visionComparison conditions not established | 44.2 | Model Card Reported by a third party |
Evaluated revision not stated | 2026-05-12 |
| MathArena/aime_2026 | Task MathArena/aime_2026Metric MathArena/aime_2026Comparison conditions not established | 37.5 | Model Card Reported by a third party |
Evaluated revision not stated | 2026-03-02 |
| TIGER-Lab/MMLU-Pro | Task mmlu_proMetric mmlu_proComparison conditions not established | 60 | Model Card Reported by a third party |
Evaluated revision not stated | 2026-04-02 |
| llamaindex/ExtractBench | Task longMetric longSetup Pipeline name: gemma4_e2b_vllm_extract_oneshot_structured_output_fileComparison conditions not established | 14.58 | ExtractBench Reported by a third party |
Evaluated revision not stated | 2026-08-24 |
| llamaindex/ExtractBench | Task meanMetric meanSetup Pipeline name: gemma4_e2b_vllm_extract_oneshot_structured_output_fileComparison conditions not established | 51.85 | ExtractBench Reported by a third party |
Evaluated revision not stated | 2026-08-24 |
| llamaindex/ExtractBench | Task mediumMetric mediumSetup Pipeline name: gemma4_e2b_vllm_extract_oneshot_structured_output_fileComparison conditions not established | 28.96 | ExtractBench Reported by a third party |
Evaluated revision not stated | 2026-08-24 |
| llamaindex/ExtractBench | Task shortMetric shortSetup Pipeline name: gemma4_e2b_vllm_extract_oneshot_structured_output_fileComparison conditions not established | 63.71 | ExtractBench Reported by a third party |
Evaluated revision not stated | 2026-08-24 |
SAVRN's Notes on gemma-4-E2B-it
Text, images and audio go in, text comes out, and this instruction-tuned checkpoint runs in 12.3 GB at 16-bit, 6.1 GB at 8-bit, 3.1 GB at 4-bit. On the least expensive card the Index prices for it, a single MI300X at $1.85 an hour on-demand, most of the 192 GB stays free for the 131,072 token window. At 5.1 billion parameters and more than 140 languages, it is sized for one card running multilingual assistants that read pictures and hear speech.
Under Apache 2.0 you can modify, redistribute and sell what you build on it, keeping the license and notice files and stating significant changes, with an express patent grant included. Look at the context figure: the configuration says 131,072 tokens while Google's family description says up to 256K, so confirm which your stack honors. No host prices per million tokens are listed, and its pre-trained base is google/gemma-4-E2B.
SAVRN's Notes on Qwen2.5-Omni-3B
We file this one under whole voice assistant in a single checkpoint. Qwen2.5-Omni-3B takes text, images, audio and video and answers in text and streamed speech. The 3B in the name undersells it: the file holds 5.5 billion parameters in bfloat16, 12 GB across 18 files. Memory in use is 13.3 GB at 16-bit, 6.6 GB at 8-bit and 3.3 GB at 4-bit, so even full precision fits on nearly any accelerator you already own. The cheapest rental we track is one MI300X at $1.85 an hour, which is paying for 192 GB to use 13.
Two things to settle first. The license is recorded as other with no summary, so put the publisher's terms in front of counsel before a commercial speech product. And no context length is on record, so measure how much audio or video one request holds before promising a session length. The weights date from April 30, 2025 with no update since; the paper is arXiv:2503.20215.
Questions
Which is larger, gemma-4-E2B-it or Qwen2.5-Omni-3B?
Qwen2.5-Omni-3B (5.5B parameters) is larger than gemma-4-E2B-it (5.1B parameters), by the parameter counts their publishers report.
Which is cheaper to run, gemma-4-E2B-it or Qwen2.5-Omni-3B?
At 4-bit, gemma-4-E2B-it fits on 1x MI300X from $1.85 an hour and Qwen2.5-Omni-3B on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use gemma-4-E2B-it commercially?
Yes. gemma-4-E2B-it 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.