SAVRN
Search Contact SAVRN

SAVRN Model Hub · Comparisons

OLMo-2-0425-1B vs Qwen2.5-1.5B-Instruct

OLMo-2-0425-1B has 1.5B parameters and Qwen2.5-1.5B-Instruct has 1.5B parameters; both are released under Apache License 2.0; at 16-bit, OLMo-2-0425-1B needs about 3.6 GB (1x MI300X from $1.85 an hour) and Qwen2.5-1.5B-Instruct about 3.7 GB (1x MI300X from $1.85 an hour).

Published metadata for 2 models, each read from its own repository.
Field OLMo-2-0425-1B
allenai/OLMo-2-0425-1B
Qwen2.5-1.5B-Instruct
Qwen/Qwen2.5-1.5B-Instruct
Publisher Ai2 Qwen
Task Text generation Text generation
Modality Text Text
Parameters, as reported 1.5B parameters 1.5B parameters
Architecture Olmo2ForCausalLM Qwen2ForCausalLM
Library transformers transformers
Context length 4,096 tokens 32,768 tokens
Repository size 5.9 GB 3.1 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) 3.6 GB 3.7 GB
Cheapest GPUs at 16-bit, per hour 1x MI300X, $1.85 1x MI300X, $1.85
Memory at 4-bit (weights and margin) 0.9 GB 0.9 GB
Cheapest GPUs at 4-bit, per hour 1x MI300X, $1.85 1x MI300X, $1.85
Revision viewed a1847dff3500 989aa7980e4c
Downloads reported by the hub 794k 7.2M
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 OLMo-2-0425-1B

Three gigabytes at 16-bit, 1.8 GB at 8-bit, under a gigabyte at 4-bit. Those figures decide where Ai2's 1.5-billion-parameter text model lives in a facility, and the answer is almost anywhere. The cheapest configuration in our data is one MI300X with 192 GB at $1.85 an hour, a card that could hold dozens of copies. We would run it beside a larger model rather than on its own hardware, and the 4,096-token context suits short prompts and short answers.

Apache 2.0 permits commercial use, modification and redistribution, asks you to keep the notices and state significant changes, and carries an express patent grant. The paper trail is the draw: Ai2 released code, checkpoints, logs and training details, naming OLMo-mix-1124 for pretraining and Dolmino-mix-1124 for mid-training. Check that your stack runs transformers 4.48 or later, and note the weights ship in float32, so the 5.9 GB on disk halves at 16-bit.

SAVRN's Notes on Qwen2.5-1.5B-Instruct

When the job is turning text into JSON, reading tables or writing past 8K tokens on a slice of a card, Qwen2.5-1.5B-Instruct is the size class to look at. Its 16-bit weights are 3.1 GB and need 3.7 GB to run; 8-bit needs 1.9 GB and 4-bit 0.9 GB. At $1.85 an hour, the cheapest Index setup is a single MI300X with 192 GB, room for more than fifty copies of the 16-bit footprint, so packing the card sets your cost per instance.

Apache 2.0 permits commercial use, changes and redistribution if the license and notices stay attached and you state significant changes. Measure the 32,768-token context against your longest input, note that it is derived from the Qwen2.5-1.5B base with weights dated September 2024, and that no host has this one on the Index yet, so the card is the only price on the table.

Questions

Which is larger, OLMo-2-0425-1B or Qwen2.5-1.5B-Instruct?

Qwen2.5-1.5B-Instruct (1.5B parameters) is larger than OLMo-2-0425-1B (1.5B parameters), by the parameter counts their publishers report.

Which is cheaper to run, OLMo-2-0425-1B or Qwen2.5-1.5B-Instruct?

At 4-bit, OLMo-2-0425-1B fits on 1x MI300X from $1.85 an hour and Qwen2.5-1.5B-Instruct on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.

Can I use OLMo-2-0425-1B commercially?

Yes. OLMo-2-0425-1B 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 Qwen2.5-1.5B-Instruct commercially?

Yes. Qwen2.5-1.5B-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.

Related Comparisons