SAVRN
Search Contact SAVRN

SAVRN Model Hub · Comparisons

Qwen3.5-4B vs Qwen3-VL-4B-Instruct

Qwen3.5-4B has 4.7B parameters and Qwen3-VL-4B-Instruct has 4.4B parameters; both are released under Apache License 2.0; at 16-bit, Qwen3.5-4B needs about 11.2 GB (1x MI300X from $1.85 an hour) and Qwen3-VL-4B-Instruct about 10.7 GB (1x MI300X from $1.85 an hour).

Published metadata for 2 models, each read from its own repository.
Field Qwen3.5-4B
Qwen/Qwen3.5-4B
Qwen3-VL-4B-Instruct
Qwen/Qwen3-VL-4B-Instruct
Publisher Qwen Qwen
Task Image and text to text Image and text to text
Modality Image and text Image and text
Parameters, as reported 4.7B parameters 4.4B parameters
Architecture Qwen3_5ForConditionalGeneration Qwen3VLForConditionalGeneration
Library transformers transformers
Context length 262,144 tokens 262,144 tokens
Repository size 9.3 GB 8.9 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) 11.2 GB 10.7 GB
Cheapest GPUs at 16-bit, per hour 1x MI300X, $1.85 1x MI300X, $1.85
Memory at 4-bit (weights and margin) 2.8 GB 2.7 GB
Cheapest GPUs at 4-bit, per hour 1x MI300X, $1.85 1x MI300X, $1.85
Revision viewed 851bf6e806ef ebb281ec70b0
Downloads reported by the hub 7M 3.8M
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.

Qwen3.5-4B

BenchmarkConditionsResultReported byRevisionDate
Idavidrein/gpqa Task diamondMetric diamondComparison conditions not established 76.2 Model Card
Reported by a third party
Evaluated revision not stated 2026-03-02
LiquidAI/ifstruct-v1.0 Task ifstruct_v1Metric ifstruct_v1Comparison conditions not established 36.25 Liquid AI — IFStruct v1.0 blog (Qwen3.5-4B)
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 66.3 Model Card
Reported by a third party
Evaluated revision not stated 2026-04-28
TIGER-Lab/MMLU-Pro Task mmlu_proMetric mmlu_proComparison conditions not established 79.1 Model Card
Reported by a third party
Evaluated revision not stated 2026-03-02
likaixin/ScreenSpot-Pro Task overallMetric overallComparison conditions not established 60.3 Model Card
Reported by a third party
Evaluated revision not stated 2026-03-18
llamaindex/ExtractBench Task longMetric longSetup Pipeline name: qwen3_5_4b_vllm_extract_oneshot_structured_output_fileComparison conditions not established 27.31 ExtractBench
Reported by a third party
Evaluated revision not stated 2026-08-26
llamaindex/ExtractBench Task meanMetric meanSetup Pipeline name: qwen3_5_4b_vllm_extract_oneshot_structured_output_fileComparison conditions not established 82.43 ExtractBench
Reported by a third party
Evaluated revision not stated 2026-08-26
llamaindex/ExtractBench Task mediumMetric mediumSetup Pipeline name: qwen3_5_4b_vllm_extract_oneshot_structured_output_fileComparison conditions not established 76.64 ExtractBench
Reported by a third party
Evaluated revision not stated 2026-08-26
llamaindex/ExtractBench Task shortMetric shortSetup Pipeline name: qwen3_5_4b_vllm_extract_oneshot_structured_output_fileComparison conditions not established 89.06 ExtractBench
Reported by a third party
Evaluated revision not stated 2026-08-26
llamaindex/ParseBench Task chartMetric chartSetup Pipeline name: qwen3_5_4b_vllm_layoutComparison conditions not established 2.5 ParseBench
Reported by a third party
Evaluated revision not stated 2026-04-14
llamaindex/ParseBench Task layoutMetric layoutSetup Pipeline name: qwen3_5_4b_vllm_layoutComparison conditions not established 19.7 ParseBench
Reported by a third party
Evaluated revision not stated 2026-04-14
llamaindex/ParseBench Task meanMetric meanSetup Pipeline name: qwen3_5_4b_vllm_layoutComparison conditions not established 35.4 ParseBench
Reported by a third party
Evaluated revision not stated 2026-04-14
llamaindex/ParseBench Task tableMetric tableSetup Pipeline name: qwen3_5_4b_vllm_layoutComparison conditions not established 8 ParseBench
Reported by a third party
Evaluated revision not stated 2026-04-14
llamaindex/ParseBench Task text_contentMetric text_contentSetup Pipeline name: qwen3_5_4b_vllm_layoutComparison conditions not established 88.9 ParseBench
Reported by a third party
Evaluated revision not stated 2026-04-14
llamaindex/ParseBench Task text_formattingMetric text_formattingSetup Pipeline name: qwen3_5_4b_vllm_layoutComparison conditions not established 57.8 ParseBench
Reported by a third party
Evaluated revision not stated 2026-04-14

Qwen3-VL-4B-Instruct

BenchmarkConditionsResultReported byRevisionDate
tiiuae/PBench Task averageMetric averageSetup Detection-only model combined with SAM2 to convert boxes to segmentation masks.Comparison conditions not established 49.2 Community Evals
Reported by a third party
Evaluated revision not stated 2026-05-11

SAVRN's Notes on Qwen3.5-4B

A 262,144-token window on a 4.7B model shapes everything else here. It is built on Qwen3.5-4B-Base and reads images as well as text. At 16-bit it needs 11.2 GB to run, so on the cheapest setup we list, one MI300X with 192 GB at $1.85 an hour on demand, quantizing is a choice, not a requirement; 4-bit brings it to 2.8 GB for several copies on one card.

Apache 2.0 means you can run it commercially, fine-tune it and redistribute what you make, as long as the license and any NOTICE file stay attached and you state significant changes, with a patent grant included. Before committing, run the window length you intend to use and measure memory there; 11.2 GB is the entry ticket, not the ceiling. Released February 27, 2026, it is young; check the publisher's page for revisions before you freeze a version.

SAVRN's Notes on Qwen3-VL-4B-Instruct

Feed it an image and a question and it answers in text. At 4.4B parameters the memory figures put it on shared hardware: 2.7 GB needed at 4-bit, 5.3 GB at 8-bit, 10.7 GB for the full 16-bit weights. The cheapest Index setup is one MI300X with 192 GB at $1.85 an hour on-demand, a price set by the card rather than the model, so a single copy leaves most of that card idle.

Apache 2.0 permits commercial use, modification and redistribution, so a fine-tuned version can ship inside a product if the license and copyright notices travel with it and significant changes are stated. Confirm the 262,144-token context length, the ceiling on how much image and text goes into one request, and check that the files you receive match the October 11, 2025 release. Four linked technical reports carry the lineage back to the Qwen-VL paper.

Questions

Which is larger, Qwen3.5-4B or Qwen3-VL-4B-Instruct?

Qwen3.5-4B (4.7B parameters) is larger than Qwen3-VL-4B-Instruct (4.4B parameters), by the parameter counts their publishers report.

Which is cheaper to run, Qwen3.5-4B or Qwen3-VL-4B-Instruct?

At 4-bit, Qwen3.5-4B fits on 1x MI300X from $1.85 an hour and Qwen3-VL-4B-Instruct on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.

Can I use Qwen3.5-4B commercially?

Yes. Qwen3.5-4B 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 Qwen3-VL-4B-Instruct commercially?

Yes. Qwen3-VL-4B-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