{"id":10499,"date":"2026-10-07T11:08:05","date_gmt":"2026-10-07T02:08:05","guid":{"rendered":"https:\/\/localmodelwatch.tsuchitsuchi.com\/model-google-gemma-4-e4b-en\/"},"modified":"2026-11-02T23:08:13","modified_gmt":"2026-11-02T14:08:13","slug":"model-google-gemma-4-e4b-en","status":"publish","type":"page","link":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/model-google-gemma-4-e4b-en\/","title":{"rendered":"gemma-4-E4B Guide: VRAM Requirements, GGUF Builds, Model Files"},"content":{"rendered":"

Everything Local Model Watch has published about the gemma-4-E4B<\/strong> family: 1 article(s) covering the base model and its fine-tunes, plus converted builds we tracked after publication. Memory requirements below are computed by this site from file sizes, not quoted from model cards. Part of our model family index<\/a>.<\/p>\n

At a Glance<\/h2>\n
\n\n\n\n\n\n\n\n\n\n\n
Item<\/th>\nValue<\/th>\n<\/tr>\n<\/thead>\n
Base model(s)<\/td>\ngoogle\/gemma-4-E4B<\/a><\/td>\n<\/tr>\n
Publisher<\/td>\nGoogle<\/a><\/td>\n<\/tr>\n
Parameters<\/td>\n8.0B<\/td>\n<\/tr>\n
License (model card)<\/td>\napache-2.0<\/td>\n<\/tr>\n
Smallest VRAM tier<\/td>\n8GB<\/td>\n<\/tr>\n
Articles<\/td>\n1<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n

Hardware Requirements<\/h2>\n

Estimated requirements (calculated by Local Model Watch)<\/strong> \u2014 8.0B parameters<\/p>\n

\n\n\n\n\n\n
Your VRAM<\/th>\nQuantization<\/th>\nFile size<\/th>\nEst. memory needed<\/th>\n<\/tr>\n<\/thead>\n
8GB (RTX 4060 \/ 3060 Ti, etc.)<\/td>\nQ4_K_M<\/td>\n4.9GB<\/td>\n5.9GB<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n

Memory estimates add a 20% runtime overhead (KV cache, etc.) to the actual size of the distributed files. Actual usage varies with context length, batch size and inference engine. These figures are computed by this site from file sizes, not published by the model’s authors. Compare with other models in our VRAM quick reference<\/a>. What the quantization names mean: glossary<\/a>.<\/em><\/p>\n

Figures are for google\/DiarizationLM-Gemma-4-E4B-v1, the most recent model in this family with a hardware estimate.<\/em><\/p>\n

Can You Run It Locally?<\/h2>\n

Runs in Ollama, LM Studio and llama.cpp as-is.<\/strong><\/p>\n

It is distributed in GGUF, so no conversion is needed.<\/p>\n

License \u2014 apache-2.0<\/code> (Commercial use allowed):<\/strong> Permits commercial use, modification and redistribution. Redistribution requires including the license and stating changes; includes a patent grant.<\/p>\n

Compression:<\/strong> the Q4_K_M build measures 5.26 bits per weight \u2014 about 33% the size of the original 16-bit weights, calculated by this site from the actual file sizes.<\/p>\n

Compiled by this site’s code from the published formats, converted builds we have found, and each engine’s own model registry. “Not found” means we have not seen such a build, not that none exists. License summaries are not legal advice \u2014 check the publisher’s original terms before relying on them.<\/em><\/p>\n

Distributed Files<\/h2>\n

Weight files published in google\/DiarizationLM-Gemma-4-E4B-v1<\/a>, listed by this site from the Hugging Face API. Sizes are the actual file sizes.<\/em><\/p>\n

\n\n\n\n\n\n\n\n
File<\/th>\nSize<\/th>\n<\/tr>\n<\/thead>\n
DiarizationLM-Gemma-4-E4B-v1-q4_0.gguf<\/code><\/td>\n5.15GB<\/td>\n<\/tr>\n
DiarizationLM-Gemma-4-E4B-v1-q4_k_m.gguf<\/code><\/td>\n5.30GB<\/td>\n<\/tr>\n
model.safetensors<\/code><\/td>\n15.99GB<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n

Quantized and Converted Variants<\/h2>\n
\n

\u2192 Scroll horizontally to see all columns<\/p>\n\n\n\n\n\n
Added<\/th>\nPublisher<\/th>\nFormat<\/th>\nRepository<\/th>\nSmallest VRAM tier (build, est. memory)<\/th>\n<\/tr>\n<\/thead>\n
2026-10-06<\/td>\nmradermacher<\/td>\nGGUF<\/td>\nmradermacher\/DiarizationLM-Gemma-4-E4B-v1-GGUF<\/a><\/td>\nQ6_K 6.9GB (fits in 8GB VRAM)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n

File sizes of each build:<\/p>\n