HF Model & Benchmark Matrix

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

AceInstruct-1.5B-GGUF

Mungert/AceInstruct-1.5B-GGUF

kind
gguf
quant
gguf (16-bit)
family
misc
modality
text-generation
root model
nvidia/AceInstruct-1.5B
provider
Mungert
license
cc-by-nc-4.0
language
en
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
40
likes
3
created
—
last modified
2025-09-24T15:44:18+00:00 (2025)
huggingface
https://huggingface.co/Mungert/AceInstruct-1.5B-GGUF
tags
ggufnvidiaAceInstructcodemathgeneral_domaininstruct_modelpytorchtext-generationenarxiv:2412.15084license:cc-by-nc-4.0endpoints_compatibleregion:usconversational

Benchmark scores (6)

benchmarkcategoryscorecontextconfevidence
GSM8Kmath73.2GSM8Kmedium| GSM8K | 73.20 | 80.44 | 91.60 | 93.10 | 95.80 | 96.36 |
MBPPcoding63.2MBPPmedium| MBPP | 63.20 | 65.76 | 79.20 | 74.32 | 88.20 | 83.66 |
HumanEvalcoding61.6HumanEvalmedium| HumanEval | 61.60 | 73.17 | 84.80 | 85.37 | 86.60 | 89.63 |
MMLUknowledge58.37MMLUmedium| MMLU | 58.37 | 58.17 | 74.51 | 74.68 | 84.67 | 83.88 |
MATHmath55.2MATHmedium| MATH | 55.20 | 60.34 | 75.50 | 76.40 | 83.10 | 84.50 |
MMLU-Proknowledge32.4MMLU Promedium| MMLU Pro | 32.40 | 33.78 | 56.30 | 54.50 | 71.10 | 66.10 |

Discussions (0)

none scraped.

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