AI Model Rankings

Best models for every use case, ranked by quality and sorted by minimum VRAM. Find the best model your hardware can run.

💬

Chat & General

General-purpose language models for conversation, writing, and reasoning

#	Model	Author	Params	Min VRAM	Action
1	SmolLM2 135M	HuggingFace	0.135B	0.64GB	Check
2	SmolLM2 360M	HuggingFace	0.36B	0.75GB	Check
3	Danube 3 500M	H2O.ai	0.5B	0.8GB	Check
4	Qwen 2.5 0.5B	Alibaba	0.5B	0.96GB	Check
5	TinyLlama 1.1B	TinyLlama	1.1B	1.12GB	Check
6	Llama 3.2 1B Instruct	Meta	1.24B	1.25GB	Check
7	Gemma 3 1B	Google	1B	1.25GB	Check
8	SmolLM2 1.7B	HuggingFace	1.7B	1.48GB	Check
9	Falcon 3 1B	TII	1B	1.48GB	Check
10	Qwen 2.5 1.5B	Alibaba	1.5B	1.54GB	Check
11	DeepSeek R1 Distill 1.5B	DeepSeek	1.5B	1.54GB	Check
12	Granite 3.3 2B	IBM	2B	1.94GB	Check
13	EXAONE 3.5 2.4B	LG AI	2.4B	2.03GB	Check
14	StableLM Zephyr 3B	Stability AI	3B	2.09GB	Check
15	Rocket 3B	Pansophic	3B	2.09GB	Check
16	Gemma 2 2B	Google	2.6B	2.09GB	Check
17	Falcon 3 3B	TII	3B	2.37GB	Check
18	Llama 3.2 3B Instruct	Meta	3.2B	2.38GB	Check
19	Qwen 2.5 3B	Alibaba	3B	2.46GB	Check
20	Danube 3 4B	H2O.ai	4B	2.73GB	Check
21	Phi-3.5 Mini 3.8B	Microsoft	3.8B	2.73GB	Check
22	Gemma 3 4B	Google	4B	2.82GB	Check
23	Phi-4 Mini 3.8B	Microsoft	3.8B	2.82GB	Check
24	Nemotron Mini 4B	NVIDIA	4B	3.01GB	Check
25	Yi 1.5 6B Chat	01.AI	6B	3.92GB	Check
26	Mistral 7B Instruct v0.3	Mistral AI	7.3B	4.57GB	Check
27	OpenChat 3.5 7B	OpenChat	7B	4.57GB	Check
28	OLMo 2 7B	Allen AI	7B	4.67GB	Check
29	InternLM 2.5 7B	Shanghai AI Lab	7.7B	4.89GB	Check
30	EXAONE 3.5 7.8B	LG AI	7.8B	4.94GB	Check
31	Falcon 3 7B	TII	7B	5GB	Check
32	DeepSeek R1 Distill 8B	DeepSeek	8B	5.08GB	Check
33	Llama 3.1 8B Instruct	Meta	8B	5.08GB	Check
34	Granite 3.3 8B	IBM	8B	5.1GB	Check
35	Qwen 2.5 7B Instruct	Alibaba	7.6B	5.3GB	Check
36	Yi 1.5 9B Chat	01.AI	9B	5.46GB	Check
37	Gemma 2 9B Instruct	Google	9.2B	5.87GB	Check
38	Falcon 3 10B	TII	10B	6.36GB	Check
39	Solar 10.7B	Upstage	10.7B	6.52GB	Check
40	Gemma 3 12B	Google	12B	7.3GB	Check
41	Mistral Nemo 12B	Mistral AI	12B	7.46GB	Check
42	Qwen 2.5 14B	Alibaba	14B	8.87GB	Check
43	Phi-4	Microsoft	14B	8.93GB	Check
44	Mistral Small 22B	Mistral AI	22B	12.93GB	Check
45	Gemma 3 27B	Google	27B	15.91GB	Check
46	Qwen 2.5 32B	Alibaba	32B	18.99GB	Check
47	Llama 3.1 70B Instruct	Meta	70B	40.1GB	Check

💻

Coding

Specialized models for code generation, completion, and debugging

#	Model	Author	Params	Min VRAM	Action
1	Qwen 2.5 Coder 0.5B	Alibaba	0.5B	1.13GB	Check
2	DeepSeek Coder 1.3B	DeepSeek	1.3B	1.31GB	Check
3	Yi Coder 1.5B	01.AI	1.5B	1.4GB	Check
4	Qwen 2.5 Coder 1.5B	Alibaba	1.5B	1.54GB	Check
5	CodeGemma 2B	Google	2B	2.02GB	Check
6	Stable Code 3B	Stability AI	3B	2.09GB	Check
7	StarCoder2 3B	BigCode	3B	2.26GB	Check
8	Qwen 2.5 Coder 3B	Alibaba	3B	2.46GB	Check
9	Code Llama 7B	Meta	7B	4.3GB	Check
10	DeepSeek Coder 6.7B	DeepSeek	6.7B	4.3GB	Check
11	StarCoder2 7B	BigCode	7B	4.66GB	Check
12	Qwen 2.5 Coder 7B	Alibaba	7.6B	4.86GB	Check
13	Yi Coder 9B	01.AI	9B	5.46GB	Check
14	CodeGemma 7B	Google	8.5B	5.46GB	Check
15	Code Llama 13B Instruct	Meta	13B	7.83GB	Check
16	Qwen 2.5 Coder 14B	Alibaba	14B	8.87GB	Check

🎨

Image Generation

Text-to-image models for art, photos, and design

#	Model	Author	Params	Min VRAM	Action
1	Stable Diffusion 2.1 Base (CoreML)	Stability AI / Apple	0.86B	1.56GB	Check
2	Stable Diffusion 1.5 (GGUF)	Runway / GPUStack	0.86B	2.13GB	Check
3	Stable Diffusion 1.5 (CoreML)	Runway	0.86B	2.5GB	Check
4	Stable Diffusion 2.1 (GGUF)	Stability AI	0.86B	2.66GB	Check
5	Stable Diffusion XL (CoreML)	Stability AI	3.5B	3.34GB	Check
6	SDXL Turbo (GGUF)	Stability AI	3.5B	5GB	Check
7	Stable Diffusion 3 Medium (GGUF)	Stability AI	2.5B	9.15GB	Check
8	FLUX.1 Schnell (GGUF)	Black Forest Labs	12B	14GB	Check
9	FLUX.1 Dev (GGUF)	Black Forest Labs	12B	14GB	Check

🎤

Speech-to-Text

Transcription and speech recognition models

#	Model	Author	Params	Min VRAM	Action
1	Whisper Tiny English (Quantized)	OpenAI	0.039B	0.1GB	Check
2	Whisper Tiny	OpenAI	0.039B	0.2GB	Check
3	Whisper Base	OpenAI	0.074B	0.3GB	Check
4	Whisper Base English	OpenAI	0.074B	0.3GB	Check
5	Whisper Small	OpenAI	0.24B	0.95GB	Check
6	Distil-Whisper Large v3	HuggingFace	0.76B	1.92GB	Check
7	Whisper Medium	OpenAI	0.77B	1.93GB	Check
8	Whisper Large v3 Turbo	OpenAI	0.81B	2.01GB	Check
9	Whisper Large v3	OpenAI	1.55B	3.38GB	Check

🔊

Text-to-Speech

Voice synthesis and text-to-speech models

#	Model	Author	Params	Min VRAM	Action
1	Piper TTS - Amy (English)	Rhasspy	0.02B	0.15GB	Check
2	Piper TTS - Lessac (English)	Rhasspy	0.02B	0.15GB	Check
3	Piper TTS - Spanish (MLS)	Rhasspy	0.02B	0.15GB	Check
4	Piper TTS - German (Thorsten)	Rhasspy	0.02B	0.15GB	Check
5	Piper TTS - Chinese (Huayan)	Rhasspy	0.02B	0.15GB	Check
6	Piper TTS - Japanese (Kokoro)	Rhasspy	0.02B	0.15GB	Check
7	Piper TTS - Korean	Rhasspy	0.02B	0.15GB	Check
8	Piper TTS - Russian (Irina)	Rhasspy	0.02B	0.15GB	Check
9	Piper TTS - Portuguese (Faber)	Rhasspy	0.02B	0.15GB	Check
10	Piper TTS - Arabic (Kareem)	Rhasspy	0.02B	0.15GB	Check
11	Piper TTS - French (Siwis)	Rhasspy	0.02B	0.53GB	Check
12	Piper TTS - Italian (Riccardo)	Rhasspy	0.02B	0.53GB	Check
13	Piper TTS - LibriTTS-R (English)	Rhasspy	0.02B	0.57GB	Check
14	Kokoro 82M TTS	Kokoro	0.082B	0.58GB	Check

🎵

Audio Generation

AI music and audio creation

#	Model	Author	Params	Min VRAM	Action
1	MusicGen Small	Meta	0.3B	0.78GB	Check

👁️

Multimodal / Vision

Models that understand both images and text

#	Model	Author	Params	Min VRAM	Action
1	Qwen2-VL 2B	Alibaba	2.2B	1.42GB	Check
2	Moondream 2	Moondream	1.8B	1.5GB	Check
3	MiniCPM-V 2.6	OpenBMB	2B	2.1GB	Check
4	PaliGemma 3B	Google	3B	2.5GB	Check
5	Phi-3.5 Vision	Microsoft	4.2B	3.2GB	Check
6	LLaVA 1.6 7B	LLaVA	7B	5GB	Check

🔗

Embedding

Text embedding models for search and retrieval

#	Model	Author	Params	Min VRAM	Action
1	BGE Small EN v1.5	BAAI	0.033B	0.1GB	Check
2	Snowflake Arctic Embed S	Snowflake	0.033B	0.1GB	Check
3	all-MiniLM-L6-v2	Sentence Transformers	0.023B	0.1GB	Check
4	Nomic Embed Text v1.5	Nomic AI	0.137B	0.3GB	Check
5	BGE Large EN v1.5	BAAI	0.335B	0.83GB	Check

Can't Run the Model You Want?

Cloud GPUs give you instant access to any model, any size.

RunPod — from $0.25/hr Vast.ai — from $0.15/hr

Need a GPU upgrade?

See our Best GPU for AI buying guide