# gemma-4-31B-it vs Qwen2.5-VL-32B-Instruct: Specs and GPU Cost
Source: https://savrn.com/models/compare/gemma-4-31b-it-vs-qwen2-5-vl-32b-instruct
Markdown alternate of the page above; the site index is https://savrn.com/llms.txt

---

| Field | [gemma-4-31B-it](https://savrn.com/models/gemma-4-31b-it) google/gemma-4-31B-it | [Qwen2.5-VL-32B-Instruct](https://savrn.com/models/qwen2-5-vl-32b-instruct) Qwen/Qwen2.5-VL-32B-Instruct |
| --- | --- | --- |
| Publisher | Google | Qwen |
| Task | Image and text to text | Image and text to text |
| Modality | Image and text | Image and text |
| Parameters, as reported | 31.3B parameters | 33.5B parameters |
| Architecture | Gemma4ForConditionalGeneration | Qwen2_5_VLForConditionalGeneration |
| Library | transformers | transformers |
| Context length | 262,144 tokens | 128,000 tokens |
| Repository size | 62.6 GB | 68.3 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) | 75.1 GB | 80.3 GB |
| Cheapest GPUs at 16-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Memory at 4-bit (weights and margin) | 18.8 GB | 20.1 GB |
| Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Revision viewed | 842da3794eaa | 7cfb30d71a1f |
| Downloads reported by the hub | 8.6M | 1.1M |
| Last observed | 2026-10-23 | 2026-09-22 |

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-4-31B-it

| Benchmark | Conditions | Result | Reported by | Revision | Date |
| --- | --- | --- | --- | --- | --- |
| Idavidrein/gpqa | Task diamondMetric diamondComparison conditions not established | 84.3 | [Model Card](https://huggingface.co/google/gemma-4-31B-it) Reported by a third party | Evaluated revision not stated | 2026-04-02 |
| LiquidAI/ifstruct-v1.0 | Task ifstruct_v1Metric ifstruct_v1Comparison conditions not established | 95.9 | Liquid AI — IFStruct v1.0 blog (gemma-4-31B-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 | 76.9 | [Model Card](https://huggingface.co/google/gemma-4-31B-it) Reported by a third party | Evaluated revision not stated | 2026-05-12 |
| TIGER-Lab/MMLU-Pro | Task mmlu_proMetric mmlu_proComparison conditions not established | 85.2 | [Model Card](https://huggingface.co/google/gemma-4-31B-it) Reported by a third party | Evaluated revision not stated | 2026-04-02 |
| cais/hle | Task hleMetric hleSetup With searchComparison conditions not established | 26.5 | [Model Card](https://huggingface.co/google/gemma-4-31B-it) Reported by a third party | Evaluated revision not stated | 2026-04-02 |
| facebook/mmi | Task error-rateMetric error-rateComparison conditions not established | 41.1 | [MMI evaluation](https://huggingface.co/datasets/facebook/mmi) Reported by a third party | Evaluated revision not stated | 2026-10-20 |
| facebook/mmi | Task mmi-valueMetric mmi-valueComparison conditions not established | 11.19 | [MMI evaluation](https://huggingface.co/datasets/facebook/mmi) Reported by a third party | Evaluated revision not stated | 2026-10-20 |
| facebook/mmi | Task modality-presence-scoreMetric modality-presence-scoreComparison conditions not established | 14.61 | [MMI evaluation](https://huggingface.co/datasets/facebook/mmi) Reported by a third party | Evaluated revision not stated | 2026-10-20 |
| facebook/mmi | Task pass-rate-lenientMetric pass-rate-lenientComparison conditions not established | 9.63 | [MMI evaluation](https://huggingface.co/datasets/facebook/mmi) Reported by a third party | Evaluated revision not stated | 2026-10-20 |
| facebook/mmi | Task pass-rate-strictMetric pass-rate-strictComparison conditions not established | 9.18 | [MMI evaluation](https://huggingface.co/datasets/facebook/mmi) Reported by a third party | Evaluated revision not stated | 2026-10-20 |
| facebook/mmi | Task precisionMetric precisionComparison conditions not established | 100 | [MMI evaluation](https://huggingface.co/datasets/facebook/mmi) Reported by a third party | Evaluated revision not stated | 2026-10-20 |
| facebook/mmi | Task recallMetric recallComparison conditions not established | 13.29 | [MMI evaluation](https://huggingface.co/datasets/facebook/mmi) Reported by a third party | Evaluated revision not stated | 2026-10-20 |
| joelniklaus/LEXam-hard | Task lexam_hardMetric lexam_hardSetup lighteval, LEXam paper prompts, one response per question, no tools; DeepSeek-R1-0528 judge; mean of the German and English means over the 518 questions, 0-100Comparison conditions not established | 37.41 | [SwissLegalEvals per-sample details (lighteval)](https://huggingface.co/buckets/joelniklaus/SwissLegalEvals) Reported by a third party | Evaluated revision not stated | 2026-06-11 |
| llamaindex/ParseBench | Task chartMetric chartSetup Pipeline name: gemma4_31b_vllm_with_layoutComparison conditions not established | 15 | [ParseBench](https://huggingface.co/datasets/llamaindex/ParseBench) Reported by a third party | Evaluated revision not stated | 2026-04-17 |
| llamaindex/ParseBench | Task layoutMetric layoutSetup Pipeline name: gemma4_31b_vllm_with_layoutComparison conditions not established | 57.4 | [ParseBench](https://huggingface.co/datasets/llamaindex/ParseBench) Reported by a third party | Evaluated revision not stated | 2026-04-17 |
| llamaindex/ParseBench | Task meanMetric meanSetup Pipeline name: gemma4_31b_vllm_with_layoutComparison conditions not established | 62.4 | [ParseBench](https://huggingface.co/datasets/llamaindex/ParseBench) Reported by a third party | Evaluated revision not stated | 2026-04-17 |
| llamaindex/ParseBench | Task tableMetric tableSetup Pipeline name: gemma4_31b_vllm_with_layoutComparison conditions not established | 80.6 | [ParseBench](https://huggingface.co/datasets/llamaindex/ParseBench) Reported by a third party | Evaluated revision not stated | 2026-04-17 |
| llamaindex/ParseBench | Task text_contentMetric text_contentSetup Pipeline name: gemma4_31b_vllm_with_layoutComparison conditions not established | 89.9 | [ParseBench](https://huggingface.co/datasets/llamaindex/ParseBench) Reported by a third party | Evaluated revision not stated | 2026-04-17 |
| llamaindex/ParseBench | Task text_formattingMetric text_formattingSetup Pipeline name: gemma4_31b_vllm_with_layoutComparison conditions not established | 69.3 | [ParseBench](https://huggingface.co/datasets/llamaindex/ParseBench) Reported by a third party | Evaluated revision not stated | 2026-04-17 |
| sapbot/ask-my-agent-bench-2 | Task fallbackMetric fallbackComparison conditions not established | 72.1 | Not named Reported by a third party | Evaluated revision not stated | 2026-06-23 |

## SAVRN's Notes on gemma-4-31B-it

One MI300X at $1.85 per hour carries this 31.3 billion parameter Gemma at 16-bit: 62.5 GB of weights and 75.1 GB needed against the card's 192 GB. Quantizing brings that to 37.5 GB at 8-bit and 18.8 GB at 4-bit, but here it buys concurrent context, not fit. With 262,144 tokens of context and image input, we would stay at 16-bit and give the spare memory to long documents.

Apache 2.0 permits commercial use, modification and redistribution, provided the license and NOTICE file stay attached and significant changes are stated. It is the instruction-tuned build of google/gemma-4-31B, described at arXiv:2607.02770; audio input belongs to the E2B, E4B and 12B sizes, not this one. DeepInfra hosts it at $0.13 in and $0.38 out per million tokens, Novita at $0.14 and $0.40; the output rate is where your own facility makes its case.

SAVRN Research, 2026-09-18

## SAVRN's Notes on Qwen2.5-VL-32B-Instruct

Run this at 16-bit and plan for 80.3 GB: 66.9 GB of weights plus runtime, fitting one MI300X with 192 GB at $1.85 an hour, the cheapest setup we list. At 8-bit the need falls to 40.1 GB, at 4-bit to 20.1 GB, where an H100 at $1.99 also fits. The 33.5B parameters take image and text in and return text. Qwen cites a 128,000-token context while the configuration lists a 32,768-token sliding window, so test your longest inputs before sizing the KV cache.

Apache 2.0 permits commercial use with notices kept. The download line says the release comes through ModelScope, and the pull is 68.3 GB across 18 safetensors shards — plan the mirror step. The page records an AWQ quantization built from this checkpoint if you want a pre-cut 4-bit, and cites the YaRN context-extension paper alongside technical report arXiv 2502.13923. At 1.1M downloads a month it is one of the most-deployed open vision-language models in this class.

SAVRN Research

## Questions

### Which is larger, gemma-4-31B-it or Qwen2.5-VL-32B-Instruct?

Qwen2.5-VL-32B-Instruct (33.5B parameters) is larger than gemma-4-31B-it (31.3B parameters), by the parameter counts their publishers report.

### Which is cheaper to run, gemma-4-31B-it or Qwen2.5-VL-32B-Instruct?

At 4-bit, gemma-4-31B-it fits on 1x MI300X from $1.85 an hour and Qwen2.5-VL-32B-Instruct on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.

### Can I use gemma-4-31B-it commercially?

Yes. gemma-4-31B-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.

### Can I use Qwen2.5-VL-32B-Instruct commercially?

Yes. Qwen2.5-VL-32B-Instruct 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

- [gemma-4-31B-it vs Qwen3.6-35B-A3B-NVFP4](https://savrn.com/models/compare/gemma-4-31b-it-vs-qwen3-6-35b-a3b-nvfp4-3)
- [gemma-4-31B-it vs Qwen3.8-27B](https://savrn.com/models/compare/gemma-4-31b-it-vs-qwen3-8-27b)
- [Qwen2.5-VL-32B-Instruct vs Qwen3.6-35B-A3B](https://savrn.com/models/compare/qwen2-5-vl-32b-instruct-vs-qwen3-6-35b-a3b)