SAVRN Model Hub · Comparisons
Qwen2.5-VL-7B-Instruct vs Qwen2-VL-7B-Instruct
Qwen2.5-VL-7B-Instruct has 8.3B parameters and Qwen2-VL-7B-Instruct has 8.3B parameters; both are released under Apache License 2.0; at 16-bit, Qwen2.5-VL-7B-Instruct needs about 19.9 GB (1x MI300X from $1.85 an hour) and Qwen2-VL-7B-Instruct about 19.9 GB (1x MI300X from $1.85 an hour).
| Field | Qwen2.5-VL-7B-Instruct Qwen/Qwen2.5-VL-7B-Instruct | Qwen2-VL-7B-Instruct Qwen/Qwen2-VL-7B-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 | 8.3B parameters | 8.3B parameters |
| Architecture | Qwen2_5_VLForConditionalGeneration | Qwen2VLForConditionalGeneration |
| Library | transformers | transformers |
| Context length | 128,000 tokens | 32,768 tokens |
| Repository size | 16.6 GB | 16.6 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) | 19.9 GB | 19.9 GB |
| Cheapest GPUs at 16-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Memory at 4-bit (weights and margin) | 5 GB | 5 GB |
| Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Revision viewed | cc594898137f | eed13092ef92 |
| Downloads reported by the hub | 6.9M | 931.7k |
| 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.
Qwen2.5-VL-7B-Instruct
| Benchmark | Conditions | Result | Reported by | Revision | Date |
|---|---|---|---|---|---|
| MMMU/MMMU_Pro | Task mmmu_pro_visionMetric mmmu_pro_visionComparison conditions not established | 34.3 | Model Card Reported by a third party |
Evaluated revision not stated | 2026-01-28 |
| likaixin/ScreenSpot-Pro | Task android_studio_macosMetric android_studio_macosComparison conditions not established | 17.5 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
| likaixin/ScreenSpot-Pro | Task autocad_windowsMetric autocad_windowsComparison conditions not established | 0 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
| likaixin/ScreenSpot-Pro | Task blender_windowsMetric blender_windowsComparison conditions not established | 26.8 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
| likaixin/ScreenSpot-Pro | Task davinci_macosMetric davinci_macosComparison conditions not established | 22.7 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
| likaixin/ScreenSpot-Pro | Task eviews_windowsMetric eviews_windowsComparison conditions not established | 72 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
| likaixin/ScreenSpot-Pro | Task excel_macosMetric excel_macosComparison conditions not established | 20.3 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
| likaixin/ScreenSpot-Pro | Task fruitloops_windowsMetric fruitloops_windowsComparison conditions not established | 7 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
| likaixin/ScreenSpot-Pro | Task illustrator_windowsMetric illustrator_windowsComparison conditions not established | 9.7 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
| likaixin/ScreenSpot-Pro | Task inventor_windowsMetric inventor_windowsComparison conditions not established | 10 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
| likaixin/ScreenSpot-Pro | Task linux_common_linuxMetric linux_common_linuxComparison conditions not established | 20 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
| likaixin/ScreenSpot-Pro | Task macos_common_macosMetric macos_common_macosComparison conditions not established | 36.9 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
| likaixin/ScreenSpot-Pro | Task matlab_macosMetric matlab_macosComparison conditions not established | 33.3 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
| likaixin/ScreenSpot-Pro | Task origin_windowsMetric origin_windowsComparison conditions not established | 9.7 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
| likaixin/ScreenSpot-Pro | Task overallMetric overallComparison conditions not established | 26.8 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
| likaixin/ScreenSpot-Pro | Task photoshop_windowsMetric photoshop_windowsComparison conditions not established | 39.2 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
| likaixin/ScreenSpot-Pro | Task powerpoint_windowsMetric powerpoint_windowsComparison conditions not established | 39 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
| likaixin/ScreenSpot-Pro | Task premiere_windowsMetric premiere_windowsComparison conditions not established | 19.2 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
| likaixin/ScreenSpot-Pro | Task pycharm_macosMetric pycharm_macosComparison conditions not established | 19.2 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
| likaixin/ScreenSpot-Pro | Task quartus_windowsMetric quartus_windowsComparison conditions not established | 15.6 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
| likaixin/ScreenSpot-Pro | Task solidworks_windowsMetric solidworks_windowsComparison conditions not established | 9.1 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
| likaixin/ScreenSpot-Pro | Task stata_windowsMetric stata_windowsComparison conditions not established | 12.2 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
| likaixin/ScreenSpot-Pro | Task unreal_engine_windowsMetric unreal_engine_windowsComparison conditions not established | 45.7 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
| likaixin/ScreenSpot-Pro | Task vivado_windowsMetric vivado_windowsComparison conditions not established | 25 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
| likaixin/ScreenSpot-Pro | Task vmware_macosMetric vmware_macosComparison conditions not established | 58.5 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
| likaixin/ScreenSpot-Pro | Task vscode_macosMetric vscode_macosComparison conditions not established | 32.7 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
| likaixin/ScreenSpot-Pro | Task windows_common_windowsMetric windows_common_windowsComparison conditions not established | 14.8 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
| likaixin/ScreenSpot-Pro | Task word_macosMetric word_macosComparison conditions not established | 70.2 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
Qwen2-VL-7B-Instruct
| Benchmark | Conditions | Result | Reported by | Revision | Date |
|---|---|---|---|---|---|
| likaixin/ScreenSpot-Pro | Task android_studio_macosMetric android_studio_macosComparison conditions not established | 0 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
| likaixin/ScreenSpot-Pro | Task eviews_windowsMetric eviews_windowsComparison conditions not established | 12 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
| likaixin/ScreenSpot-Pro | Task fruitloops_windowsMetric fruitloops_windowsComparison conditions not established | 1.8 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
| likaixin/ScreenSpot-Pro | Task linux_common_linuxMetric linux_common_linuxComparison conditions not established | 2 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
| likaixin/ScreenSpot-Pro | Task matlab_macosMetric matlab_macosComparison conditions not established | 2.2 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
| likaixin/ScreenSpot-Pro | Task overallMetric overallComparison conditions not established | 1.6 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
| likaixin/ScreenSpot-Pro | Task powerpoint_windowsMetric powerpoint_windowsComparison conditions not established | 2.4 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
| likaixin/ScreenSpot-Pro | Task unreal_engine_windowsMetric unreal_engine_windowsComparison conditions not established | 2.9 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
| likaixin/ScreenSpot-Pro | Task vivado_windowsMetric vivado_windowsComparison conditions not established | 1.2 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
| likaixin/ScreenSpot-Pro | Task vscode_macosMetric vscode_macosComparison conditions not established | 5.5 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
| likaixin/ScreenSpot-Pro | Task word_macosMetric word_macosComparison conditions not established | 6 | ScreenSpot-Pro Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-03-17 |
SAVRN's Notes on Qwen2.5-VL-7B-Instruct
Where does a model that reads images and text and answers in text belong in a rack? Qwen2.5-VL-7B-Instruct gives three answers: 19.9 GB at 16-bit, 10.0 GB at 8-bit, 5.0 GB at 4-bit, for 8.3B parameters. The cheapest rental listed, a single 192 GB MI300X at $1.85 an hour, sits mostly idle at full precision. So we would co-locate it: run 16-bit beside whatever else the card serves, and hold the rest for a 128,000-token context.
Apache 2.0 lets you modify it, redistribute it and sell what you build; the obligations are keeping notices and stating significant changes. Check the context math: the page lists 128,000 tokens, the configuration shows a 32,768-token sliding window, and the relations point to the YaRN context extension paper, so ask your serving stack which number it honors. Then read the ScreenSpot-Pro rows by application; they span 0.0 to 72.0.
SAVRN's Notes on Qwen2-VL-7B-Instruct
Nineteen point nine gigabytes at 16-bit. That figure decides where Qwen2-VL-7B-Instruct lands, and it fits on one MI300X with room left over, at $1.85 an hour, the cheapest rate we track. At 8-bit the footprint drops to 9.9 GB and at 4-bit to 5.0 GB. The work is images and text in, text out: Qwen built it to read pictures at varied resolutions and aspect ratios and to answer questions about video longer than 20 minutes, with a 32,768-token context to hold what it sees.
Apache 2.0 allows commercial use, modification and redistribution, with notices kept. Before committing, note that the instruct weights derive from the Qwen2-VL-7B base, that the only benchmark in our record is a third-party ScreenSpot-Pro result of 1.6 overall, and that no host on the SAVRN Index prices it per token, so the hourly figure above is the cost basis.
Questions
Which is larger, Qwen2.5-VL-7B-Instruct or Qwen2-VL-7B-Instruct?
Qwen2.5-VL-7B-Instruct (8.3B parameters) is larger than Qwen2-VL-7B-Instruct (8.3B parameters), by the parameter counts their publishers report.
Which is cheaper to run, Qwen2.5-VL-7B-Instruct or Qwen2-VL-7B-Instruct?
At 4-bit, Qwen2.5-VL-7B-Instruct fits on 1x MI300X from $1.85 an hour and Qwen2-VL-7B-Instruct on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use Qwen2.5-VL-7B-Instruct commercially?
Yes. Qwen2.5-VL-7B-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.
Can I use Qwen2-VL-7B-Instruct commercially?
Yes. Qwen2-VL-7B-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.