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 | 8.5M |
| 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.
Qwen2-0.5B
| 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
At 16-bit this checkpoint needs 1.2 GB of memory, and at 4-bit only 0.3 GB. Our cheapest listed slot is still one MI300X with 192 GB at $1.85 an hour, far more than 494M parameters need, so the hardware decision is what else shares the card. This is the base model of the Qwen2 line, not the instruction-tuned one, and we read it as a starting point for your own fine-tune rather than a finished chat endpoint.
Apache 2.0 covers commercial use, modification and redistribution, with notices kept and changes stated, so a tuned derivative can ship in your product. Access is open. Two things to check: the 1.2 GB is weights plus overhead, and filling the 131,072-token context adds memory on top; and the one score in our file is 14.97 on MMLU-Pro from EvalEval, so run your own evaluation before committing.
SAVRN's Notes on Qwen2.5-0.5B-Instruct
Run this one at 16-bit and it asks for 1.2 GB of memory; 8-bit needs 0.6 GB and 4-bit 0.3 GB. The cheapest setup we list is a single 192 GB MI300X at $1.85 per hour on-demand, and we would not give 494M parameters a card of their own. It belongs on shared capacity beside larger jobs, where its 32,768 token context still covers the table reading and JSON output Qwen highlighted for the 2.5 series.
Apache 2.0 keeps the deployment simple: commercial use, modification and redistribution, provided the license, notices and NOTICE file stay attached and significant changes are stated. Two checks before committing. It was derived from the Qwen2.5-0.5B base, so if the instruct tuning does not fit, tune the base yourself. Our Index has no per-token host price for it, so that hourly card is the only cost signal, on weights last updated September 25, 2024.
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.