Home / Models / Gemma 4 E2B It
Google

Gemma 4 E2B It

Gemma 4 E2B It is an open-weights 2B-parameter model by Google. It holds an Intelligence score of 20.6 on the local.ai leaderboard (2026-08 snapshot).

edgeopen weights
20.6
local.ai Intelligence
Parameters
2B
Benchmarks (local.ai snapshot)
τ²-bench
8%
GAIA
26%
GDPval
19%
HuggingFace metadata · updated 2026-07-20
repo
google/gemma-4-E2B-it
license
apache-2.0
downloads
3,978,595
likes
896
Official HuggingFace repoOllamaCompare on the savings tool

Metadata refreshed from the HuggingFace API (snapshot 2026-08-15T15:53:42.405Z). Context length and long-form descriptions are the next pipeline stage.

Does it fit your hardware?

Detect or select your GPU first. Green = weights + context headroom, yellow = tight, grey = does not fit.

Q4_K_M 1.2GQ6_K 1.8GQ8_0 2.2GFP16 4G
Quantization≈ File sizeNote
IQ2_XXS0.5 GBExtreme compression, largest quality loss
IQ3_XXS0.7 GBVery small
Q3_K_M0.9 GBSmall
NVFP41 GBNVIDIA 4-bit
Q4_K_S1.1 GBCommon
Q4_K_M1.2 GBMost common sweet spot
Q5_K_M1.5 GBBalanced
Q6_K1.8 GBNear-lossless
Q8_02.2 GBNear-lossless
FP164 GBOriginal weights

Actual files on HuggingFace

FileSize
model.safetensors9.54 GB
GGUF: unsloth/gemma-4-E2B-it-GGUF · 472,939 downloads
FileSize
MTP/mtp-gemma-4-E2B-it-BF16.gguf0.16 GBdownload
MTP/mtp-gemma-4-E2B-it-F16.gguf0.16 GBdownload
MTP/mtp-gemma-4-E2B-it-Q8_0.gguf0.09 GBdownload
gemma-4-E2B-it-BF16.gguf8.67 GBdownload
gemma-4-E2B-it-IQ4_NL.gguf2.83 GBdownload
gemma-4-E2B-it-IQ4_XS.gguf2.78 GBdownload
gemma-4-E2B-it-Q3_K_M.gguf2.36 GBdownload
gemma-4-E2B-it-Q3_K_S.gguf2.28 GBdownload
gemma-4-E2B-it-Q4_0.gguf2.83 GBdownload
gemma-4-E2B-it-Q4_1.gguf2.94 GBdownload
gemma-4-E2B-it-Q4_K_M.gguf2.89 GBdownload
gemma-4-E2B-it-Q4_K_S.gguf2.83 GBdownload
GGUF: google/gemma-4-E2B-it-qat-q4_0-gguf · 275,121 downloads
FileSize
gemma-4-E2B-it-mmproj.gguf0.92 GBdownload
gemma-4-E2B_q4_0-it.gguf3.12 GBdownload

What you save self-hosting this model

Uses the model's own API price when it exists; otherwise the closest commercial equivalent.

Waiting for hardware detection…

Related models

Google
Gemma 4 31B It
31B params · Intelligence 66.2
Google
Gemma 4 26B A4B
26B params · Intelligence 62.8
Google
Gemma 4 12B It
12B params · Intelligence 54
Google
Diffusiongemma 26B A4B It
26B params · Intelligence 50.3

RunLocal presents third-party leaderboard data (local.ai / Exo Labs, 2026-08) with its own fit and cost estimates. Verify pricing, licenses and file sizes at the source before deploying a model.