HF Model & Benchmark Matrix

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

DeepSeek-V3.1-Terminus-GGUF

unsloth/DeepSeek-V3.1-Terminus-GGUF

kind
gguf
quant
gguf (16-bit)
family
deepseek
modality
—
root model
deepseek-ai/DeepSeek-V3.1-Terminus
provider
unsloth
license
mit
language
—
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
3,598
likes
69
created
—
last modified
2025-09-24T04:25:31+00:00 (2025)
huggingface
https://huggingface.co/unsloth/DeepSeek-V3.1-Terminus-GGUF
tags
transformersggufarxiv:2412.19437base_model:deepseek-ai/DeepSeek-V3.1-Terminusbase_model:quantized:deepseek-ai/DeepSeek-V3.1-Terminuslicense:mitendpoints_compatibleregion:usimatrixconversational

Benchmark scores (8)

benchmarkcategoryscorecontextconfevidence
SimpleQAknowledge93.4SimpleQAmedium| SimpleQA | 93.4 | 96.8 |
MMLU-Proknowledge84.8MMLU-Promedium| MMLU-Pro | 84.8 | 85.0 |
GPQA Diamondreasoning80.1GPQA-Diamondmedium| GPQA-Diamond | 80.1 | 80.7 |
LiveCodeBenchcoding74.8LiveCodeBenchmedium| LiveCodeBench | 74.8 | 74.9 |
BrowseCompagentic49.2BrowseComp-zhmedium| BrowseComp-zh | 49.2 | 45.0 |
Terminal-Benchagentic-coding31.3Terminal-benchmedium| Terminal-bench | 31.3 | 36.7 |
BrowseCompagentic30.0BrowseCompmedium| BrowseComp | 30.0 | 38.5 |
Humanity's Last Examknowledge15.9Humanity's Last Exammedium| Humanity's Last Exam | 15.9 | 21.7 |

Discussions (0)

none scraped.

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