Home / Models

Model catalog

313 models. Q4 VRAM is an estimate (Q4_K_M · 4k · batch 1), not a bench.

60/313

Model	Dev	Type	P	Ctx	Q4 est	FP16
Llama 3.1 8B	Meta	LLM	8B	128K	4.9GB	16GB
Claude 3.5 Sonnet	Anthropic	LLM	175B	200K	106.5GB	350GB
GPT-4o	OpenAI	LLM	0B	128K	—	—
Claude Opus 4.5	Anthropic	LLM	200B	200K	121.7GB	400GB
Whisper Large v3	OpenAI	Audio	1.55B	4K	0.9GB	3.1GB
Llama 4 Maverick	Meta	LLM	400B	1000K	243.4GB	800GB
Llama 3.1 70B	Meta	LLM	70B	128K	42.6GB	140GB
DeepSeek R1	DeepSeek	LLM	671B	128K	408.4GB	1342GB
Stable Diffusion XL 1.0	Stability AI	Image	6.6B	4K	4GB	13.2GB
Stable Diffusion XL 1.0	Stability AI	Image	6.6B	4K	4GB	13.2GB
Sora	OpenAI	Video	0B	4K	—	—
Llama 4 Scout	Meta	LLM	109B	10000K	66.3GB	218GB
gpt-oss 120B	OpenAI	LLM	117B	128K	71.2GB	234GB
Llama 3.3 70B	Meta	LLM	70B	128K	42.6GB	140GB
Gemma 4 31B	Google	LLM	30.7B	256K	18.7GB	61.4GB
gpt-oss 20B	OpenAI	LLM	21B	128K	12.8GB	42GB
GPT-4.1	OpenAI	LLM	0B	1048K	—	—
Gemma 4 26B-A4B	Google	LLM	25.2B	256K	15.3GB	50.4GB
Llama 3.1 405B	Meta	LLM	405B	128K	246.5GB	810GB
Mistral 7B	Mistral AI	LLM	7B	33K	4.3GB	14GB
Gemini 1.5 Pro	Google	LLM	175B	2000K	106.5GB	350GB
GPT-4o Mini	OpenAI	LLM	0B	128K	—	—
DeepSeek R1 Distill Llama 70B	DeepSeek	LLM	70B	128K	42.6GB	140GB
Claude Sonnet 4.5	Anthropic	LLM	120B	200K	73GB	240GB
Qwen2.5 Coder 32B	Alibaba	LLM	32B	131K	19.5GB	64GB
Stable Diffusion 1.5	Stability AI	Image	0.86B	4K	0.5GB	1.72GB
FLUX.1 [dev]	Black Forest Labs	Image	12B	4K	7.3GB	24GB
DALL·E 3	OpenAI	Image	12B	4K	7.3GB	24GB
Runway Gen-3 Alpha	Runway	Video	0B	4K	—	—
BGE Large EN v1.5	BAAI	Embedding	0.335B	1K	0.2GB	0.67GB
Whisper Large v3 Turbo	OpenAI	Audio	0.8B	4K	0.5GB	1.6GB
ElevenLabs Multilingual v2	ElevenLabs	Audio	1B	4K	0.6GB	2GB
Gemma 3 27B	Google	LLM	27B	128K	16.4GB	54GB
Gemma 4 12B	Google	LLM	11.95B	256K	7.3GB	23.9GB
DeepSeek R1 Distill Qwen 7B	DeepSeek	LLM	7B	128K	4.3GB	14GB
Qwen3 30B-A3B	Alibaba	LLM	30.5B	131K	18.6GB	61GB
GPT-4o	OpenAI	LLM	0B	128K	—	—
Gemma 4 E4B	Google	LLM	8B	128K	4.9GB	16GB
Qwen3 235B-A22B	Alibaba	LLM	235B	131K	143GB	470GB
Qwen3 8B	Alibaba	LLM	8B	131K	4.9GB	16GB
GPT-4.1 mini	OpenAI	LLM	0B	1048K	—	—
Gemma 4 E2B	Google	LLM	5.1B	128K	3.1GB	10.2GB
Mixtral 8x7B	Mistral AI	LLM	46.7B	33K	28.4GB	93.4GB
DeepSeek V3	DeepSeek	LLM	671B	128K	408.4GB	1342GB
Gemini 2.0 Flash	Google	Multimodal	30B	1000K	18.3GB	60GB
DeepSeek R1 Distill Qwen 32B	DeepSeek	LLM	32B	128K	19.5GB	64GB
DeepSeek R1 Distill Llama 8B	DeepSeek	LLM	8B	128K	4.9GB	16GB
Claude Opus 4.1	Anthropic	LLM	200B	200K	121.7GB	400GB
GPT-4o mini	OpenAI	LLM	0B	128K	—	—
Llama 3.3 70B Instruct	Meta	LLM	70B	128K	42.6GB	140GB
Qwen2.5 Coder 7B	Alibaba	LLM	7B	131K	4.3GB	14GB
FLUX.1 [schnell]	Black Forest Labs	Image	12B	4K	7.3GB	24GB
Veo 2	Google	Video	0B	4K	—	—
BGE-M3	BAAI	Embedding	0.568B	8K	0.3GB	1.14GB
All-MiniLM-L6-v2	Sentence Transformers	Embedding	0.022B	0K	—	0.04GB
Qwen3 32B	Alibaba	LLM	32B	131K	19.5GB	64GB
Gemma 3 12B	Google	LLM	12B	128K	7.3GB	24GB
Llama 3.2 11B Vision	Meta	Multimodal	11B	128K	6.7GB	22GB
Qwen 2.5 72B	Alibaba	LLM	72B	131K	43.8GB	144GB
Qwen 2.5 7B	Alibaba	LLM	7B	131K	4.3GB	14GB

Home / Models

Model catalog

313 models. Q4 VRAM is an estimate (Q4_K_M · 4k · batch 1), not a bench.

GPU catalog →Check fit

60/313

Model	Dev	Type	P	Ctx	Q4 est	FP16
Llama 3.1 8B	Meta	LLM	8B	128K	4.9GB	16GB
Claude 3.5 Sonnet	Anthropic	LLM	175B	200K	106.5GB	350GB
GPT-4o	OpenAI	LLM	0B	128K	—	—
Claude Opus 4.5	Anthropic	LLM	200B	200K	121.7GB	400GB
Whisper Large v3	OpenAI	Audio	1.55B	4K	0.9GB	3.1GB
Llama 4 Maverick	Meta	LLM	400B	1000K	243.4GB	800GB
Llama 3.1 70B	Meta	LLM	70B	128K	42.6GB	140GB
DeepSeek R1	DeepSeek	LLM	671B	128K	408.4GB	1342GB
Stable Diffusion XL 1.0	Stability AI	Image	6.6B	4K	4GB	13.2GB
Stable Diffusion XL 1.0	Stability AI	Image	6.6B	4K	4GB	13.2GB
Sora	OpenAI	Video	0B	4K	—	—
Llama 4 Scout	Meta	LLM	109B	10000K	66.3GB	218GB
gpt-oss 120B	OpenAI	LLM	117B	128K	71.2GB	234GB
Llama 3.3 70B	Meta	LLM	70B	128K	42.6GB	140GB
Gemma 4 31B	Google	LLM	30.7B	256K	18.7GB	61.4GB
gpt-oss 20B	OpenAI	LLM	21B	128K	12.8GB	42GB
GPT-4.1	OpenAI	LLM	0B	1048K	—	—
Gemma 4 26B-A4B	Google	LLM	25.2B	256K	15.3GB	50.4GB
Llama 3.1 405B	Meta	LLM	405B	128K	246.5GB	810GB
Mistral 7B	Mistral AI	LLM	7B	33K	4.3GB	14GB
Gemini 1.5 Pro	Google	LLM	175B	2000K	106.5GB	350GB
GPT-4o Mini	OpenAI	LLM	0B	128K	—	—
DeepSeek R1 Distill Llama 70B	DeepSeek	LLM	70B	128K	42.6GB	140GB
Claude Sonnet 4.5	Anthropic	LLM	120B	200K	73GB	240GB
Qwen2.5 Coder 32B	Alibaba	LLM	32B	131K	19.5GB	64GB
Stable Diffusion 1.5	Stability AI	Image	0.86B	4K	0.5GB	1.72GB
FLUX.1 [dev]	Black Forest Labs	Image	12B	4K	7.3GB	24GB
DALL·E 3	OpenAI	Image	12B	4K	7.3GB	24GB
Runway Gen-3 Alpha	Runway	Video	0B	4K	—	—
BGE Large EN v1.5	BAAI	Embedding	0.335B	1K	0.2GB	0.67GB
Whisper Large v3 Turbo	OpenAI	Audio	0.8B	4K	0.5GB	1.6GB
ElevenLabs Multilingual v2	ElevenLabs	Audio	1B	4K	0.6GB	2GB
Gemma 3 27B	Google	LLM	27B	128K	16.4GB	54GB
Gemma 4 12B	Google	LLM	11.95B	256K	7.3GB	23.9GB
DeepSeek R1 Distill Qwen 7B	DeepSeek	LLM	7B	128K	4.3GB	14GB
Qwen3 30B-A3B	Alibaba	LLM	30.5B	131K	18.6GB	61GB
GPT-4o	OpenAI	LLM	0B	128K	—	—
Gemma 4 E4B	Google	LLM	8B	128K	4.9GB	16GB
Qwen3 235B-A22B	Alibaba	LLM	235B	131K	143GB	470GB
Qwen3 8B	Alibaba	LLM	8B	131K	4.9GB	16GB
GPT-4.1 mini	OpenAI	LLM	0B	1048K	—	—
Gemma 4 E2B	Google	LLM	5.1B	128K	3.1GB	10.2GB
Mixtral 8x7B	Mistral AI	LLM	46.7B	33K	28.4GB	93.4GB
DeepSeek V3	DeepSeek	LLM	671B	128K	408.4GB	1342GB
Gemini 2.0 Flash	Google	Multimodal	30B	1000K	18.3GB	60GB
DeepSeek R1 Distill Qwen 32B	DeepSeek	LLM	32B	128K	19.5GB	64GB
DeepSeek R1 Distill Llama 8B	DeepSeek	LLM	8B	128K	4.9GB	16GB
Claude Opus 4.1	Anthropic	LLM	200B	200K	121.7GB	400GB
GPT-4o mini	OpenAI	LLM	0B	128K	—	—
Llama 3.3 70B Instruct	Meta	LLM	70B	128K	42.6GB	140GB
Qwen2.5 Coder 7B	Alibaba	LLM	7B	131K	4.3GB	14GB
FLUX.1 [schnell]	Black Forest Labs	Image	12B	4K	7.3GB	24GB
Veo 2	Google	Video	0B	4K	—	—
BGE-M3	BAAI	Embedding	0.568B	8K	0.3GB	1.14GB
All-MiniLM-L6-v2	Sentence Transformers	Embedding	0.022B	0K	—	0.04GB
Qwen3 32B	Alibaba	LLM	32B	131K	19.5GB	64GB
Gemma 3 12B	Google	LLM	12B	128K	7.3GB	24GB
Llama 3.2 11B Vision	Meta	Multimodal	11B	128K	6.7GB	22GB
Qwen 2.5 72B	Alibaba	LLM	72B	131K	43.8GB	144GB
Qwen 2.5 7B	Alibaba	LLM	7B	131K	4.3GB	14GB