HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

Olmo-3-1025-7B-GGUF

Mungert/Olmo-3-1025-7B-GGUF

kind
gguf
quant
gguf (16-bit)
family
olmo
modality
—
root model
allenai/Olmo-3-1025-7B
provider
Mungert
license
apache-2.0
language
en
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
296
likes
1
created
—
last modified
2025-11-24T18:20:47+00:00 (2025)
huggingface
https://huggingface.co/Mungert/Olmo-3-1025-7B-GGUF
tags
transformersggufendataset:allenai/dolma3_mix-6T-1025license:apache-2.0endpoints_compatibleregion:usconversational

Benchmark scores (12)

benchmarkcategoryscorecontextconfevidence
WinoGrandeknowledge88.6low| Marin-8B | 39.6 | 21.5 | 31.6 | 0.5 | 16.5 | 36.5 | 15.6 | 27.6 | 21.4 | 89.2 | 58.1 | 52.7 | 47.3 | 93.2 | 68.1 | 71.4 | 77.4 | 68.3 | 75.3 | 85.7 | 79.8 | 86.2 | 63.7 | 90.8 |
PIQAknowledge85.7low| Marin-8B | 39.6 | 21.5 | 31.6 | 0.5 | 16.5 | 36.5 | 15.6 | 27.6 | 21.4 | 89.2 | 58.1 | 52.7 | 47.3 | 93.2 | 68.1 | 71.4 | 77.4 | 68.3 | 75.3 | 85.7 | 79.8 | 86.2 | 63.7 | 90.8 |
HellaSwagknowledge84.0low| Marin-8B | 39.6 | 21.5 | 31.6 | 0.5 | 16.5 | 36.5 | 15.6 | 27.6 | 21.4 | 89.2 | 58.1 | 52.7 | 47.3 | 93.2 | 68.1 | 71.4 | 77.4 | 68.3 | 75.3 | 85.7 | 79.8 | 86.2 | 63.7 | 90.8 |
DROPreasoning63.7low| Marin-8B | 39.6 | 21.5 | 31.6 | 0.5 | 16.5 | 36.5 | 15.6 | 27.6 | 21.4 | 89.2 | 58.1 | 52.7 | 47.3 | 93.2 | 68.1 | 71.4 | 77.4 | 68.3 | 75.3 | 85.7 | 79.8 | 86.2 | 63.7 | 90.8 |
MMLUknowledge58.1low| Marin-8B | 39.6 | 21.5 | 31.6 | 0.5 | 16.5 | 36.5 | 15.6 | 27.6 | 21.4 | 89.2 | 58.1 | 52.7 | 47.3 | 93.2 | 68.1 | 71.4 | 77.4 | 68.3 | 75.3 | 85.7 | 79.8 | 86.2 | 63.7 | 90.8 |
BBHreasoning55.6low| Marin-8B | 39.6 | 21.5 | 31.6 | 0.5 | 16.5 | 36.5 | 15.6 | 27.6 | 21.4 | 89.2 | 58.1 | 52.7 | 47.3 | 93.2 | 68.1 | 71.4 | 77.4 | 68.3 | 75.3 | 85.7 | 79.8 | 86.2 | 63.7 | 90.8 |
MedQAdomain47.3low| Marin-8B | 39.6 | 21.5 | 31.6 | 0.5 | 16.5 | 36.5 | 15.6 | 27.6 | 21.4 | 89.2 | 58.1 | 52.7 | 47.3 | 93.2 | 68.1 | 71.4 | 77.4 | 68.3 | 75.3 | 85.7 | 79.8 | 86.2 | 63.7 | 90.8 |
MATHmath39.6low| Marin-8B | 39.6 | 21.5 | 31.6 | 0.5 | 16.5 | 36.5 | 15.6 | 27.6 | 21.4 | 89.2 | 58.1 | 52.7 | 47.3 | 93.2 | 68.1 | 71.4 | 77.4 | 68.3 | 75.3 | 85.7 | 79.8 | 86.2 | 63.7 | 90.8 |
MMLU-Proknowledge38.8low| Marin-8B | 39.6 | 21.5 | 31.6 | 0.5 | 16.5 | 36.5 | 15.6 | 27.6 | 21.4 | 89.2 | 58.1 | 52.7 | 47.3 | 93.2 | 68.1 | 71.4 | 77.4 | 68.3 | 75.3 | 85.7 | 79.8 | 86.2 | 63.7 | 90.8 |
MBPPcoding36.5low| Marin-8B | 39.6 | 21.5 | 31.6 | 0.5 | 16.5 | 36.5 | 15.6 | 27.6 | 21.4 | 89.2 | 58.1 | 52.7 | 47.3 | 93.2 | 68.1 | 71.4 | 77.4 | 68.3 | 75.3 | 85.7 | 79.8 | 86.2 | 63.7 | 90.8 |
HumanEvalcoding31.6low| Marin-8B | 39.6 | 21.5 | 31.6 | 0.5 | 16.5 | 36.5 | 15.6 | 27.6 | 21.4 | 89.2 | 58.1 | 52.7 | 47.3 | 93.2 | 68.1 | 71.4 | 77.4 | 68.3 | 75.3 | 85.7 | 79.8 | 86.2 | 63.7 | 90.8 |
BigCodeBenchcoding21.5low| Marin-8B | 39.6 | 21.5 | 31.6 | 0.5 | 16.5 | 36.5 | 15.6 | 27.6 | 21.4 | 89.2 | 58.1 | 52.7 | 47.3 | 93.2 | 68.1 | 71.4 | 77.4 | 68.3 | 75.3 | 85.7 | 79.8 | 86.2 | 63.7 | 90.8 |

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.