Hugging Face model family · google
gemma-4-E2B model family
Trace gemma-4-E2B and its 1,228 community derivatives back to the base model. Model Dig maps the lineage of GGUF quantizations, merges, adapters and fine-tunes, ranked by download heat and likes — so you can see exactly how each variant relates to gemma-4-E2B.
Open interactive lineage graph → Browse all families
1,229 models in family
440 GGUF variants
98,857 base downloads
2026-03-02 base released
Popular gemma-4-E2B derivatives
| # | Model | Author | Downloads | Likes |
|---|---|---|---|---|
| 1 | gemma-4-E2B-it | ⬇ 2,974,420 | ♥ 1,130 | |
| 2 | gemma-4-E2B-it-litert-lm LiteRT | litert-community | ⬇ 1,425,761 | ♥ 547 |
| 3 | gemma-4-E2B-it-GGUF GGUF | unsloth | ⬇ 676,362 | ♥ 356 |
| 4 | gemma-4-E2B-it-Artemis-GGUF GGUFllama.cpp | turintech | ⬇ 618,628 | ♥ 14 |
| 5 | embeddinggemma-2 | ⬇ 517,987 | ♥ 3,357 | |
| 6 | gemma-4-E2B-it-qat-w4a16-ct QATW4A16 | ⬇ 341,030 | ♥ 19 | |
| 7 | gemma-4-E2B-it-qat-mobile-GGUF GGUFQAT | unsloth | ⬇ 330,726 | ♥ 49 |
| 8 | gemma-4-E2B-it-GGUF GGUF | ggml-org | ⬇ 262,635 | ♥ 96 |
| 9 | gemma-4-E2B-it-MLX-4bit 4-bitMLX | lmstudio-community | ⬇ 227,666 | ♥ 5 |
| 10 | gemma-4-E2B-it-MLX-8bit 8-bitMLX | lmstudio-community | ⬇ 219,353 | ♥ 2 |
| 11 | gemma-4-E2B-it-MLX-5bit 5-bitMLX | lmstudio-community | ⬇ 217,553 | ♥ 0 |
| 12 | gemma-4-E2B-it-MLX-6bit 6-bitMLX | lmstudio-community | ⬇ 217,451 | ♥ 0 |
| 13 | gemma-4-E2B-it-qat-q4_0-gguf GGUFQ4_0QAT | ⬇ 169,911 | ♥ 169 | |
| 14 | gemma-4-E2B-it-GGUF GGUF | lmstudio-community | ⬇ 121,143 | ♥ 20 |
| 15 | Gemma-4-E2B-Uncensored-HauhauCS-Aggressive AggressiveUncensored | HauhauCS | ⬇ 108,888 | ♥ 380 |
| 16 | gemma-4-E2B-it-unsloth-bnb-4bit 4-bitbitsandbytes | unsloth | ⬇ 81,196 | ♥ 11 |
| 17 | gemma-4-E2B-it-qat-GGUF GGUFQAT | unsloth | ⬇ 65,988 | ♥ 107 |
| 18 | gemma-4-E2B-it | unsloth | ⬇ 62,901 | ♥ 19 |
| 19 | google_gemma-4-E2B-it-GGUF GGUF | bartowski | ⬇ 59,344 | ♥ 41 |
| 20 | gemma-4-E2B-it-assistant | ⬇ 49,971 | ♥ 83 | |
| 21 | gemma-4-e2b-uncensored-litertlm Uncensored | PeppX | ⬇ 40,946 | ♥ 34 |
| 22 | gemma-4-E2B-it-AWQ-INT4 AWQINT4 | cyankiwi | ⬇ 34,140 | ♥ 6 |
| 23 | gemma-4-E2B-it-GGUF GGUF | ente-ai | ⬇ 31,942 | ♥ 0 |
| 24 | gemma-4-e2b-it-4bit 4-bit | mlx-community | ⬇ 25,512 | ♥ 39 |
| 25 | gemma-4-E2B-it-oQ4e-mtp MTPoQ4e | Jundot | ⬇ 24,154 | ♥ 2 |
| 26 | gemma-4-E2B-it-uncensored-GGUF GGUFUncensored | TrevorJS | ⬇ 20,986 | ♥ 69 |
| 27 | Gemma-4-E2B-it-LocalAI | weareapexcreators | ⬇ 18,569 | ♥ 0 |
| 28 | gemma-4-E2B-it-qat-mobile QAT | mlx-community | ⬇ 16,481 | ♥ 3 |
| 29 | gemma-4-E2B-it-ultra-uncensored-heretic-GGUF GGUFHereticUncensored | llmfan46 | ⬇ 15,660 | ♥ 41 |
| 30 | Huihui-gemma-4-E2B-it-qat-q4_0-unquantized-abliterated-GGUF AbliteratedGGUFQ4_0QAT | huihui-ai | ⬇ 15,531 | ♥ 18 |
| 31 | gemma-4-E2B-it-GGUF GGUFllama.cpp | AtomicChat | ⬇ 14,204 | ♥ 0 |
| 32 | gemma-4-E2B-it-heretic-v1-i1-GGUF GGUFHeretici1 | mradermacher | ⬇ 11,337 | ♥ 2 |
| 33 | gemma-4-E2B-it-qat-q4_0-unquantized Q4_0QAT | ⬇ 9,486 | ♥ 43 | |
| 34 | gemma-4-E2B-it-heretic-ara-GGUF GGUFHereticARA | mradermacher | ⬇ 6,836 | ♥ 27 |
| 35 | Forge-1-Gemma-4-E2B | YoSaNoo | ⬇ 6,514 | ♥ 27 |
| 36 | gemma-4-E2B-it-ONNX ONNX RT | onnx-community | ⬇ 6,398 | ♥ 38 |
| 37 | gemma-4-E2B-it-text-ExecuTorch Text | software-mansion | ⬇ 6,229 | ♥ 3 |
| 38 | gemma4-E2B-it-qat-Q4-unsloth-heretic HereticQATQ4 | MobiusDevelopment | ⬇ 5,658 | ♥ 2 |
| 39 | Gemma-4-E2B-it-ARA-Abliterated-i1-GGUF AbliteratedGGUFARAi1 | mradermacher | ⬇ 4,525 | ♥ 1 |
| 40 | gemma-4-E2B-i1-GGUF GGUFi1 | mradermacher | ⬇ 4,476 | ♥ 2 |
Techniques in this family
GGUFQATUncensoredHereticllama.cppi1Abliterated4-bitQ4_0MLXARAONNX RTMAXvLLM8-bitbitsandbytes
Other model families
Qwen3.8-27BQwen · 1,128 models
ERNIE-5.5-Flash-Basebaidu · 5 models
DeepSeek-V4-Prodeepseek-ai · 460 models
DeepSeek-V4.1-Flash-1017deepseek-ai · 529 models
gemma-4-12Bgoogle · 1,135 models
gemma-4-26B-A4Bgoogle · 1,131 models
gemma-4-31Bgoogle · 1,215 models
gemma-4-E4Bgoogle · 1,189 models
LFM3-1.7BLiquidAI · 364 models
MiniMax-M2.5MiniMaxAI · 170 models
Kimi-K3moonshotai · 504 models
MiniCPM5-2Bopenbmb · 440 models
Qwen3.5-4B-BaseQwen · 555 models
Qwen3.5-9B-BaseQwen · 960 models
Qwen3.8-Flash-NextQwen · 1,230 models
Hy3tencent · 165 models
Inkling-2-Smallthinkingmachines · 35 models
Inkling-Smallthinkingmachines · 183 models
Inklingthinkingmachines · 341 models
GLM-5.3-Flashzai-org · 645 models
GLM-5.3zai-org · 1,008 models