SAVRN Model Hub · Comparisons
Qwen2-0.5B vs Qwen2.5-0.5B-Instruct
Qwen2-0.5B has 494M parameters and Qwen2.5-0.5B-Instruct has 494M parameters; both are released under Apache License 2.0; at 16-bit, Qwen2-0.5B needs about 1.2 GB (1x MI300X from $1.85 an hour) and Qwen2.5-0.5B-Instruct about 1.2 GB (1x MI300X from $1.85 an hour).
| Field | Qwen2-0.5B Qwen/Qwen2-0.5B | Qwen2.5-0.5B-Instruct Qwen/Qwen2.5-0.5B-Instruct |
|---|---|---|
| Publisher | Qwen | Qwen |
| Task | Text generation | Text generation |
| Modality | Text | Text |
| Parameters, as reported | 494M parameters | 494M parameters |
| Architecture | Qwen2ForCausalLM | Qwen2ForCausalLM |
| Library | transformers | transformers |
| Context length | 131,072 tokens | 32,768 tokens |
| Repository size | 999.6 MB | 999.6 MB |
| 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) | 1.2 GB | 1.2 GB |
| Cheapest GPUs at 16-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Memory at 4-bit (weights and margin) | 0.3 GB | 0.3 GB |
| Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Revision viewed | 91d2aff3f957 | 7ae557604adf |
| Downloads reported by the hub | 752.5k | 6M |
| Last observed | 2026-09-18 | 2026-10-16 |
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.
Qwen2-0.5B
| Benchmark | Conditions | Result | Reported by | Revision | Date |
|---|---|---|---|---|---|
| TIGER-Lab/MMLU-Pro | Task mmlu_proMetric mmlu_proComparison conditions not established | 14.97 | EvalEval Reported by a third party |
Evaluated revision not stated | 2026-06-30 |
SAVRN's Notes on Qwen2-0.5B
494M parameters, 988.1 MB on disk, 1.2 GB at 16-bit and 0.3 GB at 4-bit: this is the smallest Qwen2 entry and, at 752.5k downloads a month, one of the most-used base models on the hub. The $1.85 MI300X hour is the table's answer, but the honest host is a phone-class GPU or a spare slot on an existing box.
Apache 2.0 permits commercial use and fine-tuning with notices kept. The 131,072-token context is generous for the size, though the third-party MMLU-Pro score on file, 14.97, reminds you this is a raw pretrained model — it will not follow instructions out of the box. Use it as a fine-tuning substrate, an eval harness baseline, or an embedded text component; if you need answers, the Instruct sibling is one slot over.
SAVRN's Notes on Qwen2.5-0.5B-Instruct
494M parameters, a 32,768-token context, 1.2 GB at 16-bit and 0.3 GB at 4-bit: the smallest Qwen2.5 instruct is a routing, tagging and drafting utility, not a chat endpoint — and the one 192 GB MI300X at $1.85 an hour we list as its cheapest setup is hardware it should share, or skip the GPU entirely with the community GGUF conversions.
Apache 2.0 keeps deployment simple: commercial use, modification, redistribution, notices kept. The 10 files give you a single 988.1 MB safetensors in bfloat16, weights last updated September 25, 2024. Its 8.7M monthly downloads say most users treat it as a component — turn detectors, math models and edge ports fill the derived list. The card claims the family traits of long-context support and 29-plus languages; at this size, benchmark rather than assume.
Questions
Which is larger, Qwen2-0.5B or Qwen2.5-0.5B-Instruct?
Qwen2-0.5B (494M parameters) is larger than Qwen2.5-0.5B-Instruct (494M parameters), by the parameter counts their publishers report.
Which is cheaper to run, Qwen2-0.5B or Qwen2.5-0.5B-Instruct?
At 4-bit, Qwen2-0.5B fits on 1x MI300X from $1.85 an hour and Qwen2.5-0.5B-Instruct on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use Qwen2-0.5B commercially?
Yes. Qwen2-0.5B 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 Qwen2.5-0.5B-Instruct commercially?
Yes. Qwen2.5-0.5B-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.