whatmodel.sh / Olmo 3 7B Think DPO
Olmo 3 7B Think DPO
↗ share
+ contribute
Olmo 3 7B Think DPO is an open-weights language model from Ai2, released November 2025. Its published size is 7.3B parameters. Licence: apache-2.0.
Catalogue identity notes
Comparison-only, proposed so the Olmo-3-7B-Think card's MATH and OMEGA runs count. The pinned card (@d97e442) has a 'DPO' stage row linking [Olmo-3-7B-Think-DPO](https://huggingface.co/allenai/Olmo-3-7B-Think-DPO) and an evaluation column 'Olmo 3 Think 7B DPO'. Weights: allenai/Olmo-3-7B-Think-DPO (sha 7b18bf927b430ff06376fdfa5610eb3b1b6a5c38, created 2025-11-18, apache-2.0, 7,298,011,136 parameters in safetensors metadata). The DPO stage before RLVR; distinct from the final olmo-3-7b-think.
$ how it compares
The LLMs ranked either side of Olmo 3 7B Think DPO, out of 1132 with a score, then more from Ai2.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 457 |  Haha-7B | 54±6 | local | ||
| 458 |  GPT-4 Turbo Preview (1106) | 54±1 | comparison only | ||
| 459 | Olmo 3 7B Think DPO | 54±3 | local | ||
| 460 | GPT-4o Search Preview (2025-03-11) | 54±5 | api $4.38/M | ||
| 461 |  Llama3-OpenBioLLM-70B | 54±3 | local | ||
| more from Ai2 | |||||
| 329 | Olmo 3.1 32B Think | 58±1 | local | ||
| 334 | Olmo 3 32B Think | 58±1 | local | ||
| 411 | Molmo 2 8B | 55±2 | local | ||
$ what it's good at
math▁▂▃▅▆▅▄█▄▁▁▁ #175 of 400 * · 97% of its score · 2 tests
Beats MiniMax-M2.1, Mistral Medium 3.5 (128B), GPT-4.1 here, though they rank higher overall. Trails OpenThinker3 7B, Olmo 3 7B Think here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| MATH (subset unspecified) lab | 92.4% ✎ | ▃·····▃···▅█ beats 1/6 | 50% |
| OMEGA (math generalisation) lab | 40.5% ✎ | ▄······█▄▄·█ beats 4/6 | 47% |
$ where to run it
llama.cpp · recommended
version
- Install llama.cpp · Homebrew and winget installs name the commands llama-cli and llama-server instead.macOS / Linux
curl -LsSf https://llama.app/install.sh | shWindowsirm https://llama.app/install.ps1 | iex - Run Olmo 3 7B Think DPO · needs ~4.5 GB · from huggingface.co/mradermacherchat in the terminal
llama cli -hf mradermacher/Olmo-3-7B-Think-DPO-GGUF:Q4_K_M - Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf mradermacher/Olmo-3-7B-Think-DPO-GGUF:Q4_K_M
LM Studio
version
- Install LM Studio · Open the app once before using the lms command.
- Run Olmo 3 7B Think DPO · needs ~4.5 GB · from huggingface.co/mradermacher
- Or download it in the terminal
lms get https://huggingface.co/mradermacher/Olmo-3-7B-Think-DPO-GGUF@Q4_K_M -y - Then run lms ls to see its name, and lms chat followed by that name
Ollama
version
- Install Ollama
download it (macOS / Windows) ↗
Linuxcurl -fsSL https://ollama.com/install.sh | sh - Run Olmo 3 7B Think DPO · needs ~4.5 GB · from huggingface.co/mradermacherchat in the terminal
ollama run hf.co/mradermacher/Olmo-3-7B-Think-DPO-GGUF:Q4_K_M
Weights and documentation: huggingface.co/allenai ↗
$ how the score was worked out · allenai/Olmo-3-7B-Think model… 97%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 allenai/Olmo-3-7B-Think model card · lab-reported | 2 | 97% |
| prior · pull toward the middle | 3% | |
| weighted average | = 53.8 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json