SAVRN Model Hub · Comparisons
Qwen2.5-0.5B-Instruct vs Qwen3-0.6B-Base
Qwen2.5-0.5B-Instruct has 494M parameters and Qwen3-0.6B-Base has 596M parameters; both are released under Apache License 2.0; at 16-bit, Qwen2.5-0.5B-Instruct needs about 1.2 GB (1x MI300X from $1.85 an hour) and Qwen3-0.6B-Base about 1.4 GB (1x MI300X from $1.85 an hour).
| Field | Qwen2.5-0.5B-Instruct Qwen/Qwen2.5-0.5B-Instruct | Qwen3-0.6B-Base Qwen/Qwen3-0.6B-Base |
|---|---|---|
| Publisher | Qwen | Qwen |
| Task | Text generation | Text generation |
| Modality | Text | Text |
| Parameters, as reported | 494M parameters | 596M parameters |
| Architecture | Qwen2ForCausalLM | Qwen3ForCausalLM |
| Library | transformers | transformers |
| Context length | 32,768 tokens | 32,768 tokens |
| Repository size | 999.6 MB | 1.2 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) | 1.2 GB | 1.4 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 | 0.4 GB |
| Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Revision viewed | 7ae557604adf | da87bfb608c1 |
| Downloads reported by the hub | 8.5M | 871.6k |
| 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.
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.
SAVRN's Notes on Qwen3-0.6B-Base
We read the Base suffix before anything else. Qwen3-0.6B-Base is the pretrained checkpoint you post-train into an assistant, so the memory figures mean something different. A 16-bit copy takes 1.4 GB, 8-bit 0.7 GB, 4-bit 0.4 GB, and the cheapest slot we price is one 192 GB MI300X at $1.85 an hour, leaving nearly the whole card for training state, batches and the 32,768-token context. At 596 million parameters, fit is not the question; the split between training and serving is.
Apache 2.0 permits commercial use, so a derivative you train is yours to sell, provided the original notices stay attached and you state what changed. The page lists no reported evaluations and no SAVRN Index host prices, so pull the Qwen3 technical report at arXiv:2505.09388 and confirm the 32,768-token context suits your documents. Released April 28, 2025, updated July 26, 2025; get the later files.
Questions
Which is larger, Qwen2.5-0.5B-Instruct or Qwen3-0.6B-Base?
Qwen3-0.6B-Base (596M parameters) is larger than Qwen2.5-0.5B-Instruct (494M parameters), by the parameter counts their publishers report.
Which is cheaper to run, Qwen2.5-0.5B-Instruct or Qwen3-0.6B-Base?
At 4-bit, Qwen2.5-0.5B-Instruct fits on 1x MI300X from $1.85 an hour and Qwen3-0.6B-Base on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
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.
Can I use Qwen3-0.6B-Base commercially?
Yes. Qwen3-0.6B-Base 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.