Multilingual GGUF models

98 GGUF models in the Multilingual family, quantized by 61 uploaders. Sizes run from 23M to 8.03B parameters. The longest trained context is 128K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
MU
multilingual e5 large instruct
Multilingual · Ralriki
Params559M
Context512
Q4_K_M0.4 GB
GGUF
MU
multilingual e5 small
Multilingual · cstr
Params118M
Context512
Smallest0.1 GB
Embedding
MU
multilingual e5 small
Multilingual · TwinSunsLLC
Params118M
Context511
Smallest0.1 GB
Embedding
MU
multilingual e5 small gguf q8 0
Multilingual · keisuke-miyako
Params118M
Context512
Smallest0.1 GB
GGUF
MU
multilingual e5 base Q4 K M
Multilingual · dinab
Params277M
Context512
Q4_K_M0.2 GB
Embedding
MU
Multilingual TTS 1.7B Base
Multilingual · mradermacher
Params1.85B
Context32K
Q4_K_M1.2 GB
ReasoningTool use
MU
dragonkue-KoEn-E5-Tiny
Multilingual · exp-models
Params37M
Context512
Q4_K_M0.0 GB
Embedding
MU
multilingual e5 large
Multilingual · cstr
Params559M
Context514
Smallest0.4 GB
Embedding
MU
Multilingual TTS 1.7B
Multilingual · mradermacher
Params1.85B
Context32K
Q4_K_M1.2 GB
ReasoningTool use
MU
Multilingual Text Semantic Search Siamese BERT V1
Multilingual · mradermacher
Params23M
Context512
Q4_K_M0.0 GB
Embedding
MU
multilingual e5 small
Multilingual · hdrrayan
Params118M
Context511
Smallest0.2 GB
Embedding
MU
multilingual e5 base
Multilingual · tatsuyaaaaaaa
Params277M
Context512
Q4_K_M0.2 GB
GGUF
MU
multilingual e5 large instruct Q8 0
Multilingual · Content-AI
Params559M
Context512
Smallest0.6 GB
GGUF
MU
multilingual e5 base Q8 0
Multilingual · dinab
Params277M
Context512
Smallest0.3 GB
Embedding
MU
Multilingual Text Semantic Search Siamese BERT V1
Multilingual · mradermacher
Params23M
Context512
Q4_K_M0.0 GB
Embedding
MU
jp-music-title-encoder
Multilingual · gbnam8
Params40M
Context512
Smallest0.1 GB
CodingEmbedding
MU
multilingual e5 base
Multilingual · cstr
Params277M
Context514
Smallest0.3 GB
Embedding
MU
Multilingual TTS 1.7B Base
Multilingual · mradermacher
Params1.85B
Context32K
Q4_K_M1.2 GB
ReasoningTool use
MU
multilingual e5 base Q8A64
Multilingual · VelociQ8
Params480M
Context512
Smallest0.5 GB
GGUF
MU
multilingual e5 large instruct Q8A64
Multilingual · VelociQ8
Params834M
Context512
Smallest0.8 GB
GGUF
MU
Multilingual TTS 0.6B Base
Multilingual · mradermacher
Params663M
Context32K
Q4_K_M0.5 GB
ReasoningTool use
MU
multilingual e5 small
Multilingual · rodion-m
Params118M
Context512
Smallest0.5 GB
GGUF
MU
Multilingual TTS 4B Base
Multilingual · mradermacher
Params4.19B
Context32K
Q4_K_M2.6 GB
ReasoningTool use
MU
multilingual e5 small gguf q4 k m
Multilingual · keisuke-miyako
Params118M
Context512
Q4_K_M0.1 GB
GGUF
MU
multilingual-e5-large
Multilingual · phate334
Params559M
Context512
Q4_K_M0.4 GB
Embedding
MU
multilingual e5 large Q8 0
Multilingual · soichisumi
Params559M
Context512
Smallest0.6 GB
Embedding
MU
multilingual e5 base Q4 K M
Multilingual · groonga
Params277M
Context512
Q4_K_M0.2 GB
Embedding
MU
multilingual e5 small Q8 0
Multilingual · milimyname
Params118M
Context512
Smallest0.1 GB
GGUF
MU
Multilingual TTS 1.7B v0.1
Multilingual · mradermacher
Params1.85B
Context32K
Q4_K_M1.2 GB
ReasoningTool use
MU
epochdb embed
Multilingual · jersobh
Params118M
Context512
Smallest0.1 GB
Embedding

About the Multilingual GGUF models

Multilingual is represented on ggufmodels.com by 98 GGUF models, quantized by 61 uploaders on Hugging Face. The most downloaded are multilingual e5 large instruct, multilingual e5 small and multilingual e5 small. Parameter counts run from 23M to 8.03B, and the longest trained context window is 128K tokens.

A Q4_K_M file of a Multilingual model is between 0.0 to 4.9 GB, which is the quant most people start with. Most files come from mradermacher (13), keisuke-miyako (9) and dinab (5). The quants you will meet most often are Q8_0 (49), Q4_K_M (42), F16 (24) and Q6_K (19), where the number is how many models offer that quant.

Frequently asked questions

Which Multilingual GGUF should I download?

The most downloaded Multilingual GGUF here is multilingual e5 large instruct. 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 Multilingual model need?

Q4_K_M files of Multilingual models on this site range from 0.0 to 4.9 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 Multilingual GGUF files come from?

The most common quantizers here are mradermacher, keisuke-miyako and dinab. 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