Embeddinggemma GGUF models

88 GGUF models in the Embeddinggemma family, quantized by 69 uploaders. Sizes run from 131M to 514M parameters. The longest trained context is 256K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
EM
Embeddinggemma 300m
Embeddinggemma · ggml-org
Params308M
Context2K
Smallest0.3 GB
Embedding
EM
Embeddinggemma 2
Embeddinggemma · unsloth
Params271M
Context256K
Smallest0.2 GB
EmbeddingVision
EM
embeddinggemma-2
Embeddinggemma · ggml-org
Params271M
Context256K
Smallest0.3 GB
EmbeddingVision
EM
Embeddinggemma 300m Qat Q8_0 Unquantized
Embeddinggemma · ggml-org
Params303M
Context2K
Smallest0.3 GB
Embedding
EM
Embeddinggemma 300m
Embeddinggemma · ente-ai
Params308M
Context2K
Smallest0.3 GB
Embedding
EM
Embeddinggemma 300m Qat Q4_0 Unquantized
Embeddinggemma · unsloth
Params303M
Context2K
Smallest0.3 GB
Embedding
EM
Source Hf Embeddinggemma 2
Embeddinggemma · ngquocvinh
Params271M
Context256K
Q4_K_M0.2 GB
EmbeddingVision
EM
embeddinggemma-2
Embeddinggemma · AtomicChat
Params271M
Context256K
Q4_K_M0.2 GB
EmbeddingVision
EM
Embeddinggemma 300M Qat Q4_0 Unquantized
Embeddinggemma · ggml-org
Params303M
Context2K
Smallest0.3 GB
Embedding
EM
Sakura EmbeddingGemma 2 HighQuality
Embeddinggemma · webmp3
Params271M
Context—
Smallest0.0 GB
GGUF
EM
xVITA Embed2 zhTW
Embeddinggemma · xCloudinfo
Params271M
Context256K
Q4_K_M0.2 GB
EmbeddingVision
EM
EmbeddingGemma 300m
Embeddinggemma · lmstudio-community
Params303M
Context2K
Smallest0.2 GB
Embedding
EM
Embeddinggemma 2
Embeddinggemma · prithivMLmods
Params271M
Context256K
Q4_K_M0.2 GB
EmbeddingVision
EM
Embeddinggemma 2
Embeddinggemma · BennyDaBall
Params271M
Context256K
Smallest0.2 GB
EmbeddingVision
EM
Embeddinggemma 2
Embeddinggemma · Fastiraz
Params271M
Context256K
Smallest0.2 GB
EmbeddingVision
EM
EmbeddingGemma 2 Artemis text embeddings
Embeddinggemma · turintech
Params271M
Context256K
Smallest0.2 GB
Embedding
EM
Embeddinggemma 300m
Embeddinggemma · second-state
Params303M
Context2K
Q4_K_M0.2 GB
Embedding
EM
embeddinggemma 300m GGUF with dense modules
Embeddinggemma · cduk
Params308M
Context2K
Smallest0.2 GB
Embedding
EM
embeddinggemma 2
Embeddinggemma · yan2026
Params271M
Context256K
Q4_K_M0.2 GB
EmbeddingVision
EM
Embeddinggemma 300m
Embeddinggemma · gaianet
Params303M
Context2K
Q4_K_M0.2 GB
Embedding
EM
embeddinggemma 2 ft typed decision
Embeddinggemma · cstr
Params272M
Context—
Smallest0.3 GB
GGUF
EM
embeddinggemma 300m q4k
Embeddinggemma · metricspace
Params308M
Context2K
Smallest0.2 GB
CodingEmbedding
EM
Embeddinggemma GTAIDE 300m 2605
Embeddinggemma · nctu6
Params308M
Context2K
Q4_K_M0.2 GB
Embedding
EM
Embeddinggemma 300m
Embeddinggemma · lm-kit
Params303M
Context2K
Q4_K_M0.2 GB
Embedding
EM
embeddinggemma-2
Embeddinggemma · webmp3
Params271M
Context256K
Smallest0.2 GB
Embedding
EM
Embeddinggemma 300m
Embeddinggemma · mradermacher
Params303M
Context2K
Q4_K_M0.2 GB
Embedding
EM
Embeddinggemma 2
Embeddinggemma · empyrealworks
Params271M
Context256K
Smallest0.2 GB
Embedding
EM
embeddinggemma 2 Q8A64
Embeddinggemma · VelociQ8
Params426M
Context256K
Smallest0.4 GB
GGUF
EM
embeddinggemma 300m
Embeddinggemma · cstr
Params308M
Context2K
Smallest0.3 GB
Embedding
EM
embeddinggemma 300m Q8A64
Embeddinggemma · VelociQ8
Params514M
Context2K
Smallest0.5 GB
GGUF

About the Embeddinggemma GGUF models

Embeddinggemma is represented on ggufmodels.com by 88 GGUF models, quantized by 69 uploaders on Hugging Face. The most downloaded are Embeddinggemma 300m, Embeddinggemma 2 and embeddinggemma-2. Parameter counts run from 131M to 514M, and the longest trained context window is 256K tokens.

A Q4_K_M file of a Embeddinggemma model is between 0.2 to 0.2 GB, which is the quant most people start with. Most files come from sabafallah (4), ggml-org (4) and admiralakber (3). The quants you will meet most often are Q8_0 (48), Q4_K_M (26), BF16 (16) and Q6_K (15), where the number is how many models offer that quant.

Frequently asked questions

Which Embeddinggemma GGUF should I download?

The most downloaded Embeddinggemma GGUF here is Embeddinggemma 300m. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.

How much VRAM does a Embeddinggemma model need?

Q4_K_M files of Embeddinggemma models on this site range from 0.2 to 0.2 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.

Where do Embeddinggemma GGUF files come from?

The most common quantizers here are sabafallah, ggml-org and admiralakber. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.

Keep browsing