# gemma-4-26B-A4B-it vs Qwen3.6-35B-A3B-NVFP4 (Unsloth AI) Compared
Source: https://savrn.com/models/compare/gemma-4-26b-a4b-it-vs-qwen3-6-35b-a3b-nvfp4-2
Markdown alternate of the page above; the site index is https://savrn.com/llms.txt

---

| Field | [gemma-4-26B-A4B-it](https://savrn.com/models/gemma-4-26b-a4b-it) google/gemma-4-26B-A4B-it | [Qwen3.6-35B-A3B-NVFP4](https://savrn.com/models/qwen3-6-35b-a3b-nvfp4-2) unsloth/Qwen3.6-35B-A3B-NVFP4 |
| --- | --- | --- |
| Publisher | Google | Unsloth AI |
| Task | Image and text to text | Image and text to text |
| Modality | Image and text | Image and text |
| Parameters, as reported | 25.8B parameters | 24.6B parameters |
| Architecture | Gemma4ForConditionalGeneration | Qwen3_5MoeForConditionalGeneration |
| Library | transformers | transformers |
| Context length | 262,144 tokens | 262,144 tokens |
| Repository size | 51.6 GB | 26.5 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) | 61.9 GB | 59.1 GB |
| Cheapest GPUs at 16-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Memory at 4-bit (weights and margin) | 15.5 GB | 14.8 GB |
| Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Revision viewed | 4d7ae4984b7d | 739af1e7aac3 |
| Downloads reported by the hub | 8.6M | 1.1M |
| Last observed | 2026-10-25 | 2026-09-30 |

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-4-26B-A4B-it

| Benchmark | Conditions | Result | Reported by | Revision | Date |
| --- | --- | --- | --- | --- | --- |
| Idavidrein/gpqa | Task diamondMetric diamondComparison conditions not established | 82.3 | [Model Card](https://huggingface.co/google/gemma-4-26B-A4B-it) Reported by a third party | Evaluated revision not stated | 2026-04-02 |
| MMMU/MMMU_Pro | Task mmmu_pro_visionMetric mmmu_pro_visionComparison conditions not established | 73.8 | [Model Card](https://huggingface.co/google/gemma-4-26B-A4B-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 | 82.6 | [Model Card](https://huggingface.co/google/gemma-4-26B-A4B-it) Reported by a third party | Evaluated revision not stated | 2026-04-02 |
| cais/hle | Task hleMetric hleSetup With searchComparison conditions not established | 17.2 | [Model Card](https://huggingface.co/google/gemma-4-26B-A4B-it) Reported by a third party | Evaluated revision not stated | 2026-04-02 |
| llamaindex/ExtractBench | Task longMetric longSetup Pipeline name: gemma4_26b_vllm_extract_oneshot_structured_output_file; self-hosted on vLLM, one-shot JSON-Schema structured outputComparison conditions not established | 28.88 | [ExtractBench](https://huggingface.co/datasets/llamaindex/ExtractBench) Reported by a third party | Evaluated revision not stated | 2026-08-26 |
| llamaindex/ExtractBench | Task meanMetric meanSetup Pipeline name: gemma4_26b_vllm_extract_oneshot_structured_output_file; self-hosted on vLLM, one-shot JSON-Schema structured outputComparison conditions not established | 70.27 | [ExtractBench](https://huggingface.co/datasets/llamaindex/ExtractBench) Reported by a third party | Evaluated revision not stated | 2026-08-26 |
| llamaindex/ExtractBench | Task mediumMetric mediumSetup Pipeline name: gemma4_26b_vllm_extract_oneshot_structured_output_file; self-hosted on vLLM, one-shot JSON-Schema structured outputComparison conditions not established | 59.61 | [ExtractBench](https://huggingface.co/datasets/llamaindex/ExtractBench) Reported by a third party | Evaluated revision not stated | 2026-08-26 |
| llamaindex/ExtractBench | Task shortMetric shortSetup Pipeline name: gemma4_26b_vllm_extract_oneshot_structured_output_file; self-hosted on vLLM, one-shot JSON-Schema structured outputComparison conditions not established | 77.7 | [ExtractBench](https://huggingface.co/datasets/llamaindex/ExtractBench) Reported by a third party | Evaluated revision not stated | 2026-08-26 |
| llamaindex/ParseBench | Task chartMetric chartSetup Pipeline name: gemma4_26b_vllm_with_layoutComparison conditions not established | 14.2 | [ParseBench](https://huggingface.co/datasets/llamaindex/ParseBench) Reported by a third party | Evaluated revision not stated | 2026-04-14 |
| llamaindex/ParseBench | Task layoutMetric layoutSetup Pipeline name: gemma4_26b_vllm_with_layoutComparison conditions not established | 59.2 | [ParseBench](https://huggingface.co/datasets/llamaindex/ParseBench) Reported by a third party | Evaluated revision not stated | 2026-04-14 |
| llamaindex/ParseBench | Task meanMetric meanSetup Pipeline name: gemma4_26b_vllm_with_layoutComparison conditions not established | 58.5 | [ParseBench](https://huggingface.co/datasets/llamaindex/ParseBench) Reported by a third party | Evaluated revision not stated | 2026-04-14 |
| llamaindex/ParseBench | Task tableMetric tableSetup Pipeline name: gemma4_26b_vllm_with_layoutComparison conditions not established | 70 | [ParseBench](https://huggingface.co/datasets/llamaindex/ParseBench) Reported by a third party | Evaluated revision not stated | 2026-04-14 |
| llamaindex/ParseBench | Task text_contentMetric text_contentSetup Pipeline name: gemma4_26b_vllm_with_layoutComparison conditions not established | 83.8 | [ParseBench](https://huggingface.co/datasets/llamaindex/ParseBench) Reported by a third party | Evaluated revision not stated | 2026-04-14 |
| llamaindex/ParseBench | Task text_formattingMetric text_formattingSetup Pipeline name: gemma4_26b_vllm_with_layoutComparison conditions not established | 65.1 | [ParseBench](https://huggingface.co/datasets/llamaindex/ParseBench) Reported by a third party | Evaluated revision not stated | 2026-04-14 |

## SAVRN's Notes on gemma-4-26B-A4B-it

Gemma 4 26B A4B is the most downloaded Gemma 4 model in our catalog, at about 9.8 million a month. It is a mixture-of-experts design with 25.8B total parameters and roughly 4B active per token, so it answers with the speed of a small model and much of the knowledge of a large one. It reads text and images and keeps a 262,144-token context.

At 16-bit it needs about 62 GB, one large-memory accelerator; at 4-bit about 16 GB, which fits a workstation card. Apache 2.0 allows commercial use. For a team choosing one open multimodal model to self-host this year, this is near the top of our list.

SAVRN Research, 2026-09-18

## SAVRN's Notes on Qwen3.6-35B-A3B-NVFP4

Unsloth's NVFP4 cut of Qwen/Qwen3.6-35B-A3B: 24.6B stated parameters in a 256-expert mixture where 8 fire per token, so the 4-bit row — 12.3 GB of weights, 14.8 GB needed — is the number that matters, and the publisher says it runs on a 32 GB VRAM GPU. Our table reads 59.1 GB at 16-bit, 29.6 GB at 8-bit, 14.8 GB at 4-bit; the cheapest listed setup, one MI300X at $1.85 an hour, leaves room for the 262,144-token context.

The publisher claims 1.56x the throughput of other NVFP4 quants, calibrated on its own dataset mixed with UltraChat, benchmarked on one B200 at 128 concurrent requests — treat those as vendor numbers and test your own prompts. Apache 2.0 covers commercial use. Mind the landscape: the same base has NVFP4 builds from Red Hat AI and Ornith in this index with different stated parameter counts, so pick by serving stack and validate the checkpoint, not the name. It draws 1.1M downloads a month.

SAVRN Research

## Questions

### Which is larger, gemma-4-26B-A4B-it or Qwen3.6-35B-A3B-NVFP4?

gemma-4-26B-A4B-it (25.8B parameters) is larger than Qwen3.6-35B-A3B-NVFP4 (24.6B parameters), by the parameter counts their publishers report.

### Which is cheaper to run, gemma-4-26B-A4B-it or Qwen3.6-35B-A3B-NVFP4?

At 4-bit, gemma-4-26B-A4B-it fits on 1x MI300X from $1.85 an hour and Qwen3.6-35B-A3B-NVFP4 on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.

### Can I use gemma-4-26B-A4B-it commercially?

Yes. gemma-4-26B-A4B-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 Qwen3.6-35B-A3B-NVFP4 commercially?

Yes. Qwen3.6-35B-A3B-NVFP4 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-4-26B-A4B-it vs Qwen3.6-27B](https://savrn.com/models/compare/gemma-4-26b-a4b-it-vs-qwen3-6-27b)
- [gemma-4-26B-A4B-it vs Qwen3.8-27B](https://savrn.com/models/compare/gemma-4-26b-a4b-it-vs-qwen3-8-27b)