# dolphin-2.9.1-yi-1.5-34b vs Qwen2.5-32B-Instruct Compared
Source: https://savrn.com/models/compare/dolphin-2-9-1-yi-1-5-34b-vs-qwen2-5-32b-instruct
Markdown alternate of the page above; the site index is https://savrn.com/llms.txt

---

| Field | [dolphin-2.9.1-yi-1.5-34b](https://savrn.com/models/dolphin-2-9-1-yi-1-5-34b) dphn/dolphin-2.9.1-yi-1.5-34b | [Qwen2.5-32B-Instruct](https://savrn.com/models/qwen2-5-32b-instruct) Qwen/Qwen2.5-32B-Instruct |
| --- | --- | --- |
| Publisher | Dolphin | Qwen |
| Task | Text generation | Text generation |
| Modality | Text | Text |
| Parameters, as reported | 34.4B parameters | 32.8B parameters |
| Architecture | LlamaForCausalLM | Qwen2ForCausalLM |
| Library | transformers | transformers |
| Context length | 8,192 tokens | 32,768 tokens |
| Repository size | 68.8 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) | 82.5 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) | 20.6 GB | 19.7 GB |
| Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Revision viewed | 0141cba238d0 | 5ede1c97bbab |
| Downloads reported by the hub | 4.6M | 1.3M |
| Last observed | 2026-10-23 | 2026-10-23 |

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 dolphin-2.9.1-yi-1.5-34b

A 34.4B-parameter model that still fits one rented card: 82.5 GB at 16-bit, 41.3 GB at 8-bit, 20.6 GB at 4-bit, and the cheapest listed setup at every precision is one MI300X with 192 GB at $1.85 an hour on-demand. That makes this one of the few ways to run an unquantized 34B for under two dollars an hour. The 8,192-token context is the limit to design around — it sits well below the 32K windows on the Qwen coder and VL neighbors here — so long-document work should look at those first, and use this for what fits.

The listing records a derivation from 01-ai/Yi-1.5-34B with a LlamaForCausalLM architecture, and the disclosed training mixes — function-calling-chatml, Dolphin-2.9, dolphin-coder — point at code and tool-calling use rather than long-form prose. Apache 2.0 permits commercial use, modification and redistribution with notices kept and changes stated; read the base model's terms alongside. The repo is 24 files totaling 68.8 GB in bfloat16 safetensors, and the files last moved September 8, 2025. No Index host sells it by the token.

SAVRN Research

## SAVRN's Notes on Qwen2.5-32B-Instruct

32.8B parameters needing 78.6 GB at 16-bit — one 192 GB MI300X at $1.85 an hour still covers it with room to spare — 39.3 GB at 8-bit and 19.7 GB at 4-bit, where an H100 at $1.99 or a big workstation card also fits. The bf16 repo is 27 files totalling 65.5 GB, and the model draws 1.9M downloads a month with a 32,768-token context.

Apache 2.0 permits commercial use with notices kept. The page names an official AWQ build, Qwen2.5-32B-Instruct-AWQ, quantized from this checkpoint — the practical route to 8-bit-class memory without running your own calibration. It derives from Qwen2.5-32B and is described by arXiv:2309.00071 and arXiv:2407.10671, published 2024-09-17 with a 32,768-token context. No hosted token prices are listed; you rent by the hour or self-host.

SAVRN Research

## Questions

### Which is larger, dolphin-2.9.1-yi-1.5-34b or Qwen2.5-32B-Instruct?

dolphin-2.9.1-yi-1.5-34b (34.4B parameters) is larger than Qwen2.5-32B-Instruct (32.8B parameters), by the parameter counts their publishers report.

### Which is cheaper to run, dolphin-2.9.1-yi-1.5-34b or Qwen2.5-32B-Instruct?

At 4-bit, dolphin-2.9.1-yi-1.5-34b fits on 1x MI300X from $1.85 an hour and Qwen2.5-32B-Instruct on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.

### Can I use dolphin-2.9.1-yi-1.5-34b commercially?

Yes. dolphin-2.9.1-yi-1.5-34b 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 Qwen2.5-32B-Instruct commercially?

Yes. Qwen2.5-32B-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.

## Related Comparisons

- [dolphin-2.9.1-yi-1.5-34b vs Qwen2.5-Coder-32B-Instruct](https://savrn.com/models/compare/dolphin-2-9-1-yi-1-5-34b-vs-qwen2-5-coder-32b-instruct)
- [dolphin-2.9.1-yi-1.5-34b vs Qwen3.6-35B-A3B-abliterated-v4](https://savrn.com/models/compare/dolphin-2-9-1-yi-1-5-34b-vs-qwen3-6-35b-a3b-abliterated-v4)
- [Qwen2.5-32B-Instruct vs Qwen3-32B](https://savrn.com/models/compare/qwen2-5-32b-instruct-vs-qwen3-32b)