SAVRN Model Hub · Comparisons
Qwen3.5-2B vs Rax-4.5
Qwen3.5-2B has 2.3B parameters and Rax-4.5 has 2.3B parameters; both are released under Apache License 2.0; at 16-bit, Qwen3.5-2B needs about 5.5 GB (1x MI300X from $1.85 an hour) and Rax-4.5 about 5.5 GB (1x MI300X from $1.85 an hour).
| Field | Qwen3.5-2B Qwen/Qwen3.5-2B | Rax-4.5 raxcore-dev/Rax-4.5 |
|---|---|---|
| Publisher | Qwen | RaxCore |
| Task | Image and text to text | Image and text to text |
| Modality | Image and text | Image and text |
| Parameters, as reported | 2.3B parameters | 2.3B parameters |
| Architecture | Qwen3_5ForConditionalGeneration | Qwen3_5ForConditionalGeneration |
| Library | transformers | transformers |
| Context length | 262,144 tokens | 262,144 tokens |
| Repository size | 4.6 GB | 4.6 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) | 5.5 GB | 5.5 GB |
| Cheapest GPUs at 16-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Memory at 4-bit (weights and margin) | 1.4 GB | 1.4 GB |
| Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Revision viewed | 15852e8c1636 | 6ab58f792f61 |
| Downloads reported by the hub | 3.6M | 952.2k |
| Last observed | 2026-10-10 | 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.
Qwen3.5-2B
| Benchmark | Conditions | Result | Reported by | Revision | Date |
|---|---|---|---|---|---|
| Idavidrein/gpqa | Task diamondMetric diamondSetup GPQA DiamondComparison conditions not established | 44.9495 | EvalEval Reported by a third party |
Evaluated revision not stated | 2026-04-20 |
| LiquidAI/ifstruct-v1.0 | Task ifstruct_v1Metric ifstruct_v1Comparison conditions not established | 33.15 | Liquid AI — IFStruct v1.0 blog (Qwen3.5-2B) Reported by a third party |
Evaluated revision not stated | 2026-06-30 |
| MMMU/MMMU_Pro | Task mmmu_pro_visionMetric mmmu_pro_visionSetup ThinkingComparison conditions not established | 50.3 | 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 | 55.3 | Model Card Reported by a third party |
Evaluated revision not stated | 2026-03-02 |
| likaixin/ScreenSpot-Pro | Task overallMetric overallComparison conditions not established | 54.5 | Model Card Reported by a third party |
Evaluated revision not stated | 2026-03-18 |
| llamaindex/ExtractBench | Task longMetric longSetup Pipeline name: qwen3_5_2b_vllm_extract_oneshot_structured_output_fileComparison conditions not established | 25.93 | ExtractBench Reported by a third party |
Evaluated revision not stated | 2026-08-24 |
| llamaindex/ExtractBench | Task meanMetric meanSetup Pipeline name: qwen3_5_2b_vllm_extract_oneshot_structured_output_fileComparison conditions not established | 63.4 | ExtractBench Reported by a third party |
Evaluated revision not stated | 2026-08-24 |
| llamaindex/ExtractBench | Task mediumMetric mediumSetup Pipeline name: qwen3_5_2b_vllm_extract_oneshot_structured_output_fileComparison conditions not established | 50.93 | ExtractBench Reported by a third party |
Evaluated revision not stated | 2026-08-24 |
| llamaindex/ExtractBench | Task shortMetric shortSetup Pipeline name: qwen3_5_2b_vllm_extract_oneshot_structured_output_fileComparison conditions not established | 71.22 | ExtractBench Reported by a third party |
Evaluated revision not stated | 2026-08-24 |
| llamaindex/ParseBench | Task chartMetric chartSetup Pipeline name: qwen3_5_2b_vllm_layoutComparison conditions not established | 0.1 | ParseBench Reported by a third party |
Evaluated revision not stated | 2026-04-22 |
| llamaindex/ParseBench | Task layoutMetric layoutSetup Pipeline name: qwen3_5_2b_vllm_layoutComparison conditions not established | 18.3 | ParseBench Reported by a third party |
Evaluated revision not stated | 2026-04-22 |
| llamaindex/ParseBench | Task meanMetric meanSetup Pipeline name: qwen3_5_2b_vllm_layoutComparison conditions not established | 27.3 | ParseBench Reported by a third party |
Evaluated revision not stated | 2026-04-22 |
| llamaindex/ParseBench | Task tableMetric tableSetup Pipeline name: qwen3_5_2b_vllm_layoutComparison conditions not established | 0 | ParseBench Reported by a third party |
Evaluated revision not stated | 2026-04-22 |
| llamaindex/ParseBench | Task text_contentMetric text_contentSetup Pipeline name: qwen3_5_2b_vllm_layoutComparison conditions not established | 87.2 | ParseBench Reported by a third party |
Evaluated revision not stated | 2026-04-22 |
| llamaindex/ParseBench | Task text_formattingMetric text_formattingSetup Pipeline name: qwen3_5_2b_vllm_layoutComparison conditions not established | 31.1 | ParseBench Reported by a third party |
Evaluated revision not stated | 2026-04-22 |
SAVRN's Notes on Qwen3.5-2B
2.3B parameters, image and text in, text out, over a 262,144-token context: 5.5 GB at 16-bit, 2.7 GB at 8-bit and 1.4 GB at 4-bit on the one 192 GB MI300X at $1.85 an hour that anchors our small-model pricing — the weights take a sliver and the long context fills the rest. This is the entry point of Qwen's natively multimodal 3.5 line, first published 2026-02-28 at 4.8M downloads a month.
Apache 2.0 covers commercial use, modification and redistribution. Reported scores — GPQA Diamond 44.9495, MMLU-Pro 55.3 — set honest expectations: this is the edge and appliance tier, and the derived list includes Rockchip RK182X LLM and VLM ports, which tells you where the community is taking it. For a bigger multimodal step, the 4B sibling doubles capacity for roughly twice the memory.
SAVRN's Notes on Rax-4.5
2.3B parameters carrying a 262,144-token context with image-plus-text input. At 16-bit the weights are 4.5 GB and the run needs 5.5 GB; 8-bit is 2.7 GB and 4-bit 1.4 GB — any of them fits the cheapest card in our table, one MI300X at $1.85 an hour, and the spare room matters because a filled 262K context adds memory on top of the weights. The pull is a single 4.5 GB safetensors shard.
Apache 2.0 covers commercial use. The open question is lineage: the architecture field reads Qwen3_5ForConditionalGeneration, but the only relation on record points back to Rax-4.5 itself, so the base model and training data are unstated — ask the publisher before you depend on it. RaxCore released it November 27, 2025 and updated it July 13, 2026; no SAVRN Index host prices it, and it draws 952.2k downloads a month.
Questions
Which is larger, Qwen3.5-2B or Rax-4.5?
Qwen3.5-2B (2.3B parameters) is larger than Rax-4.5 (2.3B parameters), by the parameter counts their publishers report.
Which is cheaper to run, Qwen3.5-2B or Rax-4.5?
At 4-bit, Qwen3.5-2B fits on 1x MI300X from $1.85 an hour and Rax-4.5 on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use Qwen3.5-2B commercially?
Yes. Qwen3.5-2B 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 Rax-4.5 commercially?
Yes. Rax-4.5 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.