Multilingual AI Models

Multilingual models are trained on diverse language data, enabling them to understand and generate text in multiple languages. These models are essential for applications serving global audiences, translation tasks, cross-lingual information retrieval, and multilingual customer support. Many modern model families like Qwen, Gemma, and Mistral include strong multilingual capabilities out of the box.

43models available
0.1GB min VRAM needed

Alibaba

Qwen 2.5 7B Instruct

Efficient 7B model with strong coding and reasoning abilities.

Chat7.6B5.3-9GB VRAM
12.3M downloads3 quants

Alibaba

Qwen 2.5 1.5B

Compact 1.5B model with strong multilingual and coding abilities.

Chat1.5B1.54-2.26GB VRAM
10.0M downloads2 quants

Meta

Llama 3.1 8B Instruct

Meta's 8B parameter instruction-tuned model. Great balance of performance and efficiency for local deployment.

Chat8B5.08-17GB VRAM
9.3M downloads4 quants

Alibaba

Qwen 2.5 3B

Versatile 3B model with strong reasoning and multilingual capabilities.

Chat3B2.46-3.87GB VRAM
8.7M downloads2 quants

OpenAI

Whisper Large v3 Turbo

Optimized large Whisper model. Near-best accuracy with faster inference.

Speech0.81B2.01GB VRAM
6.4M downloads1 quants

BAAI

BGE Reranker v2 M3

Multilingual reranker. 100+ languages. 1.1GB.

0.568B1.58GB VRAM
6.2M downloads1 quants

Meta

Llama 3.2 3B Instruct

Meta's compact 3B model designed for edge and mobile deployment.

Chat3.2B2.38-3.69GB VRAM
5.7M downloads3 quants

Alibaba

Qwen 2.5 0.5B

Ultra-small 0.5B model from Alibaba. Minimal resource requirements.

Chat0.5B0.96-1.13GB VRAM
5.4M downloads2 quants

OpenAI

Whisper Large v3

Largest Whisper model. Best accuracy across all languages and accents.

Speech1.55B3.38GB VRAM
4.8M downloads1 quants

Meta

Llama 3.2 1B Instruct

Ultra-compact 1B model. Runs on virtually any device including smartphones.

Chat1.24B1.25-2.81GB VRAM
4.2M downloads3 quants

Alibaba

Qwen 2.5 32B

Premium 32B model. Top-tier reasoning. Mac with 32GB+ RAM.

Chat32B18.99GB VRAM
4.1M downloads1 quants

Alibaba

Qwen2-VL 2B

Compact vision-language model. Default multimodal model. Can understand images and answer questions about them.

Vision2.2B1.42-2.03GB VRAM
2.3M downloads2 quants

OpenAI

Whisper Small

Compact Whisper model. Good accuracy for everyday transcription tasks.

Speech0.24B0.95GB VRAM
1.9M downloads1 quants

OpenAI

Whisper Base

Base whisper model. Good balance of speed and accuracy. 142MB.

Speech0.074B0.3GB VRAM
1.5M downloads1 quants

Microsoft

Phi-3.5 Vision

Vision-language model from Microsoft. Can understand images and documents.

Vision4.2B3.2GB VRAM
1.5M downloads1 quants

Alibaba

Qwen 2.5 14B

Strong 14B model with excellent coding and reasoning. iPad Pro recommended.

Chat14B8.87-15.12GB VRAM
1.3M downloads2 quants

Microsoft

Phi-4 Mini 3.8B

Latest Phi mini with strong reasoning. Drop-in upgrade from Phi-3.5 Mini.

Chat3.8B2.82-4.3GB VRAM
1.1M downloads2 quants

Meta

Llama 3.1 70B Instruct

Meta's flagship 70B parameter model. Excellent performance rivaling GPT-4 on many benchmarks.

Chat70B40.1-142GB VRAM
985.8K downloads4 quants

OpenAI

Whisper Tiny

Tiny multilingual speech recognition. Only 75MB. Supports 99 languages. Runs on any device.

Speech0.039B0.2GB VRAM
761.0K downloads1 quants

Microsoft

Phi-3.5 Mini 3.8B

Tiny but capable 3.8B model. Runs on almost any hardware including phones.

Chat3.8B2.73-4.28GB VRAM
688.8K downloads3 quants

OpenAI

Whisper Medium

Mid-size Whisper model. Strong multilingual speech recognition.

Speech0.77B1.93GB VRAM
529.2K downloads1 quants

LG AI

EXAONE 3.5 7.8B

7.8B model from LG. Strong bilingual Korean/English.

Chat7.8B4.94-8.24GB VRAM
205.6K downloads2 quants

OpenBMB

MiniCPM-V 2.6

Efficient multimodal model with strong image understanding. Optimized for edge devices.

Vision2B2.1-3GB VRAM
143.4K downloads2 quants

Mistral AI

Mistral Nemo 12B

Mistral's 12B model with excellent instruction following.

Chat12B7.46-12.63GB VRAM
125.7K downloads2 quants

LG AI

EXAONE 3.5 2.4B

Compact model from LG. Optimized for Korean and English.

Chat2.4B2.03-3.14GB VRAM
67.7K downloads2 quants

Snowflake

Snowflake Arctic Embed S

Compact embedding model from Snowflake. Good multilingual support.

Embed0.033B0.1GB VRAM
43.2K downloads1 quants

TII

Falcon 3 7B

Full-size Falcon 3 with strong performance across benchmarks.

Chat7B5-8.3GB VRAM
23.3K downloads2 quants

Mistral AI

Mistral Small 22B

22B parameter model. Strong reasoning and multilingual. Needs 16GB+ RAM.

Chat22B12.93GB VRAM
11.8K downloads1 quants

TII

Falcon 3 1B

Ultra-compact 1B model from Technology Innovation Institute.

Chat1B1.48-2.16GB VRAM
11.3K downloads2 quants

TII

Falcon 3 3B

Compact 3B Falcon model with good performance.

Chat3B2.37-3.8GB VRAM
8.8K downloads2 quants

Rhasspy

Piper TTS - Amy (English)

Lightweight TTS voice. High quality English speech synthesis. Default TTS model - runs on any iPhone. Only 63MB.

TTS0.02B0.15GB VRAM
1 quants

Rhasspy

Piper TTS - Lessac (English)

High quality English male voice. 63MB download. Runs on any device.

TTS0.02B0.15GB VRAM
1 quants

Rhasspy

Piper TTS - LibriTTS-R (English)

Medium quality English voice with natural prosody. 63MB download.

TTS0.02B0.57GB VRAM
1 quants

Rhasspy

Piper TTS - Spanish (MLS)

Spanish female voice. Natural prosody.

TTS0.02B0.15GB VRAM
1 quants

Rhasspy

Piper TTS - French (Siwis)

French female voice.

TTS0.02B0.53GB VRAM
1 quants

Rhasspy

Piper TTS - German (Thorsten)

German male voice.

TTS0.02B0.15GB VRAM
1 quants

Rhasspy

Piper TTS - Chinese (Huayan)

Chinese Mandarin voice.

TTS0.02B0.15GB VRAM
1 quants

Rhasspy

Piper TTS - Japanese (Kokoro)

Japanese voice.

TTS0.02B0.15GB VRAM
1 quants

Rhasspy

Piper TTS - Korean

Korean voice.

TTS0.02B0.15GB VRAM
1 quants

Rhasspy

Piper TTS - Russian (Irina)

Russian female voice.

TTS0.02B0.15GB VRAM
1 quants

Rhasspy

Piper TTS - Portuguese (Faber)

Portuguese voice.

TTS0.02B0.15GB VRAM
1 quants

Rhasspy

Piper TTS - Italian (Riccardo)

Italian male voice.

TTS0.02B0.53GB VRAM
1 quants

Rhasspy

Piper TTS - Arabic (Kareem)

Arabic voice.

TTS0.02B0.15GB VRAM
1 quants

Browse Other Capabilities