Google
Gemma 4 E4B It
Gemma 4 E4B It is an open-weights 4B-parameter model by Google. It holds an Intelligence score of 28.4 on the local.ai leaderboard (2026-08 snapshot).
edgeopen weights
28.4
local.ai Intelligence
Parameters
4B
Benchmarks (local.ai snapshot)
HuggingFace metadata · updated 2026-07-20
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 2.3GQ6_K 3.6GQ8_0 4.4GFP16 8G| Quantization | ≈ File size | Note |
|---|---|---|
| IQ2_XXS | 1.1 GB | Extreme compression, largest quality loss |
| IQ3_XXS | 1.4 GB | Very small |
| Q3_K_M | 1.8 GB | Small |
| NVFP4 | 2 GB | NVIDIA 4-bit |
| Q4_K_S | 2.2 GB | Common |
| Q4_K_M | 2.3 GB | Most common sweet spot |
| Q5_K_M | 3 GB | Balanced |
| Q6_K | 3.6 GB | Near-lossless |
| Q8_0 | 4.4 GB | Near-lossless |
| FP16 | 8 GB | Original weights |
Actual files on HuggingFace
| File | Size |
|---|---|
| model.safetensors | 14.89 GB |
GGUF: lmstudio-community/gemma-4-E4B-it-GGUF · 591,023 downloads
GGUF: unsloth/gemma-4-E4B-it-GGUF · 588,730 downloads
| File | Size | |
|---|---|---|
| MTP/mtp-gemma-4-E4B-it-BF16.gguf | 0.16 GB | download |
| MTP/mtp-gemma-4-E4B-it-F16.gguf | 0.16 GB | download |
| MTP/mtp-gemma-4-E4B-it-Q8_0.gguf | 0.09 GB | download |
| gemma-4-E4B-it-BF16.gguf | 14.02 GB | download |
| gemma-4-E4B-it-IQ4_NL.gguf | 4.50 GB | download |
| gemma-4-E4B-it-IQ4_XS.gguf | 4.39 GB | download |
| gemma-4-E4B-it-Q3_K_M.gguf | 3.78 GB | download |
| gemma-4-E4B-it-Q3_K_S.gguf | 3.60 GB | download |
| gemma-4-E4B-it-Q4_0.gguf | 4.50 GB | download |
| gemma-4-E4B-it-Q4_1.gguf | 4.73 GB | download |
| gemma-4-E4B-it-Q4_K_M.gguf | 4.64 GB | download |
| gemma-4-E4B-it-Q4_K_S.gguf | 4.51 GB | download |
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…
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.