HF Model & Benchmark Matrix

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

DeepSeek-R1-0528-BF16

unsloth/DeepSeek-R1-0528-BF16

kind
original
quant
bf16 (16-bit)
family
deepseek
modality
text-generation
root model
deepseek-ai/DeepSeek-R1-0528
provider
unsloth
license
mit
language
en
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
1,284
likes
10
created
—
last modified
2025-07-14T07:07:38+00:00 (2025)
huggingface
https://huggingface.co/unsloth/DeepSeek-R1-0528-BF16
tags
transformerssafetensorsdeepseek_v3text-generationdeepseekunslothconversationalcustom_codeenarxiv:2501.12948base_model:deepseek-ai/DeepSeek-R1-0528base_model:finetune:deepseek-ai/DeepSeek-R1-0528license:mittext-generation-inferenceendpoints_compatibleregion:us

Benchmark scores (2)

benchmarkcategoryscorecontextconfevidence
GPQA Diamondreasoning71.1low| Qwen3-235B-A22B | 85.7 | 81.5 | 62.5 | 71.1 | 66.5 |
LiveCodeBenchcoding66.5low| Qwen3-235B-A22B | 85.7 | 81.5 | 62.5 | 71.1 | 66.5 |

Discussions (0)

none scraped.

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