phi-4-reasoning-unsloth-bnb-4bit

Home/Models/unsloth/phi-4-reasoning-unsloth-bnb-4bit

unsloth/phi-4-reasoning-unsloth-bnb-4bit

kind: bnb-4bit
quant: 4bit
family: phi
modality: text-generation
root model: microsoft/phi-4-reasoning
provider: unsloth
license: mit
language: en
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 113
likes: 2
created: —
last modified: 2025-05-01T10:09:57+00:00 (2025)
huggingface: https://huggingface.co/unsloth/phi-4-reasoning-unsloth-bnb-4bit
tags: transformerssafetensorsphi3text-generationphiunslothnlpmathcodechatconversationalreasoningenbase_model:microsoft/Phi-4-reasoningbase_model:quantized:microsoft/Phi-4-reasoninglicense:mittext-generation-inferenceendpoints_compatible4-bitbitsandbytesregion:us

benchmark	category	score	context	conf	evidence
HumanEval	coding	83.5	HumanEvalPlus	medium	`\| HumanEvalPlus \| 83.5 \| 92.9 \| 92.3 \| 94.0 \| 88.0 \|`
OmniMath	math	76.6		high	`\| Phi-4-reasoning \| 75.3 \| 62.9 \| 76.6 \| 65.8 \| 53.8 \|`
MMLU-Pro	knowledge	71.5	MMLUPro	medium	`\| MMLUPro \| 71.5 \| 74.3 \| 76.0 \| 79.4 \| 73.0 \|`
Chatbot Arena	chat	68.1	ArenaHard	medium	`\| ArenaHard \| 68.1 \| 73.3 \| 79.0 \| 81.9 \| 75.6 \|`
GPQA	reasoning	65.8		high	`\| Phi-4-reasoning \| 75.3 \| 62.9 \| 76.6 \| 65.8 \| 53.8 \|`
IFEval	instruction-following	62.3	IFEval Strict	medium	`\| IFEval Strict \| 62.3 \| 83.4 \| 84.9 \| 91.5 \| 81.8 \|`
LiveCodeBench	coding	53.8		high	`\| Phi-4-reasoning \| 75.3 \| 62.9 \| 76.6 \| 65.8 \| 53.8 \|`

none scraped.