HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks
Home/Models/google/gemma-4-E4B-it

gemma-4-E4B-it

google/gemma-4-E4B-it

kind
original
quant
bf16 (16-bit)
family
gemma
modality
any-to-any
root model
google/gemma-4-E4B
provider
google
license
apache-2.0
language
—
context
128K
library
transformers
vRAM (GB)
—
size on disk
—
downloads
5,732,884
likes
1,416
created
—
last modified
2026-07-20T16:42:03+00:00 (2026)
huggingface
https://huggingface.co/google/gemma-4-E4B-it
tags
transformerssafetensorsgemma4image-text-to-textany-to-anyarxiv:2607.02770base_model:google/gemma-4-E4Bbase_model:finetune:google/gemma-4-E4Blicense:apache-2.0eval-resultsendpoints_compatibledeploy:azureregion:usdeploy:sagemaker

Benchmark scores (10)

benchmarkcategoryscorecontextconfevidence
AIME 2026math89.2AIME 2026 no toolsmedium| AIME 2026 no tools | 89.2% | 88.3% | 77.5% | 42.5% | 37.5% | 20.8% |
MATHmath85.6MATH-Visionmedium| MATH-Vision | 85.6% | 82.4% | 79.7% | 59.5% | 52.4% | 46.0% |
MMLU-Proknowledge85.2MMLU Promedium| MMLU Pro | 85.2% | 82.6% | 77.2% | 69.4% | 60.0% | 67.6% |
GPQA Diamondreasoning84.3GPQA Diamondmedium| GPQA Diamond | 84.3% | 82.3% | 78.8% | 58.6% | 43.4% | 42.4% |
LiveCodeBenchcoding80.0LiveCodeBench v6medium| LiveCodeBench v6 | 80.0% | 77.1% | 72.0% | 52.0% | 44.0% | 29.1% |
MMMUmultimodal76.9MMMU Promedium| MMMU Pro | 76.9% | 73.8% | 69.1% | 52.6% | 44.2% | 49.7% |
BigBenchreasoning74.4BigBench Extra Hardmedium| BigBench Extra Hard | 74.4% | 64.8% | 53.0% | 33.1% | 21.9% | 19.3% |
Humanity's Last Examknowledge26.5HLE with searchmedium| HLE with search | 26.5% | 17.2% | - | - | - | - |
Humanity's Last Examknowledge19.5HLE no toolsmedium| HLE no tools | 19.5% | 8.7% | 5.2% | - | - | - |
WER FLEURSspeech-asr8.0FLEURS (lower is better)medium| FLEURS (lower is better) | - | - | 0.069<sup>*</sup> | 0.08 | 0.09 | - |

Discussions (44)

titleauthorstatuscommentstype
Missing Apache 2.0 LICENSE Filenamton1727open0disc
Update README.mdArturito1open0disc
Update READMEMaartenGrmerged0disc
Is there any quantization process done to this google/gemma-4-E4B-it model checkpoint?yliu0777open0disc
Raise per-image vision soft-token budget from 280 to 1120lucianommartinsopen0disc
Add response_template to tokenizer_config.jsonRocketknight1merged0disc
Add IFStruct v1.0 evaluation resultSaylorTwiftopen0disc
Chat template may re-inject prior-turn reasoning during multi-turn tool use → repetition loopsManniX-ITAopen0disc
fix: chat template — null handling, reasoning preservation, turn-tag balance, input validationlucianommartinsmerged0disc
Add EvalEval community eval resultsEvalEvalBotclosed0disc
Add MMMU-Pro evaluation resultSaylorTwiftopen0disc
Request: DOIjs9741908309open0disc
gemma-4-E4B-itpppnnndraft0disc
Fix lineageosansevieromerged0disc
fix(chat_template): Emit multimodal placeholders in tool response content-partsharshaljanjanimerged0disc
GGUF available — Cerebellum v1 & v2 (ablation-guided mixed-precision)deucebucketopen0disc
fix(chat_template): update SI and tool call handlingdougreidmerged0disc
Image Dimension Test ResultsKoitenshinopen0disc
[Bug] `enable_thinking` doesn't trigger thinking mode for E4B/E2Bmeeyeong11closed0disc
gemma-4-e4b-itGAFHdraft0disc
Add ParseBench evaluation resultsboyang-runllamaopen0disc
Thanks!JanjanJeanopen0disc
Add ParseBench evaluation resultsboyang-runllamaclosed0disc
fix: embed chat_template in tokenizer_config.jsonNERDDISCOopen0disc
fix: embed chat_template in tokenizer_config.jsonNERDDISCOclosed0disc
task-mismatchTimeLordRapsopen0disc
Request: DOIabdullahal7sanclosed0disc
[Bug] google/gemma-4-E4B-it tokenizer fails with AttributeError: 'list' object has no attribute 'keys' — extra_special_tokens format incompatibility with transformers vAIharvopen0disc
Update response schemaRocketknight1merged0disc
Error in Mistral Common Packageaniket2025open0disc
fix: prefix-preserving tool calls + dialog compliancelucianommartinsmerged0disc
fix: function calling formatting in chat templateRyanMullinsopen0disc
It doesn't process audio in video filejluixjuradoclosed0disc
Unable to quantize model using bitsandbytesdeathknight0open0disc
Impressive skills for its size, but this doesn't belong on normal peoples' phones.phil111closed0disc
How Gemma 4 models were trained?guiopenopen0disc
Gemma4-E4B has emotion vectors — first replication of Anthropic's findings on open-sourcerain1955open0disc
demofengkaiWebdraft0disc
Best modelLanguidoclosed0disc
Gemma 4 MTPshadowlilacopen0disc
Add AIME 2026 evaluation resultSaylorTwiftopen0disc
ordl-gemma-familyWinsocketclosed0disc
Add eval resultsmerveopen0disc
Proposed video configurationpcuenqmerged0disc
Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.