SAVRN Model Hub · Comparisons
Qwen2.5-Coder-32B-Instruct vs Qwen3-32B
Qwen2.5-Coder-32B-Instruct has 32.8B parameters and Qwen3-32B has 32.8B parameters; both are released under Apache License 2.0; at 16-bit, Qwen2.5-Coder-32B-Instruct needs about 78.6 GB (1x MI300X from $1.85 an hour) and Qwen3-32B about 78.6 GB (1x MI300X from $1.85 an hour).
| Field | Qwen2.5-Coder-32B-Instruct Qwen/Qwen2.5-Coder-32B-Instruct | Qwen3-32B Qwen/Qwen3-32B |
|---|---|---|
| Publisher | Qwen | Qwen |
| Task | Text generation | Text generation |
| Modality | Text | Text |
| Parameters, as reported | 32.8B parameters | 32.8B parameters |
| Architecture | Qwen2ForCausalLM | Qwen3ForCausalLM |
| Library | transformers | transformers |
| Context length | 32,768 tokens | 40,960 tokens |
| Repository size | 65.5 GB | 65.5 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) | 78.6 GB | 78.6 GB |
| Cheapest GPUs at 16-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Memory at 4-bit (weights and margin) | 19.7 GB | 19.7 GB |
| Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Revision viewed | 381fc969f78e | 9216db5781bf |
| Downloads reported by the hub | 1M | 3.2M |
| Last observed | 2026-09-30 | 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.
Qwen3-32B
| Benchmark | Conditions | Result | Reported by | Revision | Date |
|---|---|---|---|---|---|
| LEXam-Benchmark/LEXam | Task mcq_4_choicesMetric mcq_4_choicesComparison conditions not established | 45.3 | LEXam Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-06-02 |
| LEXam-Benchmark/LEXam | Task open_questionMetric open_questionComparison conditions not established | 40 | LEXam Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-06-02 |
SAVRN's Notes on Qwen2.5-Coder-32B-Instruct
78.6 GB at 16-bit is the number to plan around: 65.5 GB of weights plus runtime on one MI300X with 192 GB at $1.85 an hour. At 8-bit the footprint is 39.3 GB, at 4-bit 19.7 GB, with an H100 at $1.99 also fitting the lower two. Context is 32,768 tokens, and the configuration separately lists a 131,072-token sliding window — check both against your longest files before committing.
This is the largest of six Qwen2.5-Coder sizes and the instruct build of the 32B base. Apache 2.0 permits commercial use; the download line says the release comes through ModelScope. The economic comparison on the page is Nscale hosting it at $0.06 in and $0.20 out per million tokens — against $1.85 an hour of GPU time, token volume decides which side wins, so run your traffic through both columns. An AWQ build and even an abliterated GGUF derive from this checkpoint. It draws 1M downloads a month.
SAVRN's Notes on Qwen3-32B
Qwen3 32B is a dense model with a switch: it can think step by step for hard problems or answer directly for simple ones. With about 5 million downloads a month, it is one of the most used large open models in our catalog.
It needs about 79 GB at 16-bit, one large-memory accelerator, and about 20 GB at 4-bit. Apache 2.0 allows commercial use. Its 40,960-token context is shorter than newer Qwen releases; if you need long documents, look at Qwen3.5 27B.
Questions
Which is larger, Qwen2.5-Coder-32B-Instruct or Qwen3-32B?
Qwen2.5-Coder-32B-Instruct (32.8B parameters) is larger than Qwen3-32B (32.8B parameters), by the parameter counts their publishers report.
Which is cheaper to run, Qwen2.5-Coder-32B-Instruct or Qwen3-32B?
At 4-bit, Qwen2.5-Coder-32B-Instruct fits on 1x MI300X from $1.85 an hour and Qwen3-32B on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use Qwen2.5-Coder-32B-Instruct commercially?
Yes. Qwen2.5-Coder-32B-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 Qwen3-32B commercially?
Yes. Qwen3-32B 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.