Open-weight AI models you can run on a GPU pod
Aquanode doesn't run a hosted inference API. Every model below links to a GPU pod sized for it, billed per second, that you install your own inference stack on (or, for image and video models, our ComfyUI template). Specs, license and VRAM sizing for each of these 111 models are sourced from the model's own Hugging Face card and config, never invented. Looking for a specific model rather than these 111? The GPU recommender covers 1,800+ Hugging Face models with the same live VRAM and price math.
LLM
Llama 3.3 70B Instruct
Meta
Meta's 70B multilingual instruction-tuned chat model.
Qwen2.5 7B Instruct
Alibaba (Qwen)
A 7.6B general-purpose model with strong coding, math and structured-output skills, small enough for a single mid-range GPU.
DeepSeek-V3
DeepSeek
A 685B (MoE) language model for chat and instruction-following.
DeepSeek-V3-0324
DeepSeek
A 685B (MoE) language model for chat and instruction-following.
DeepSeek-V3.1
DeepSeek
A 685B (MoE) language model for chat and instruction-following.
DeepSeek-V3.2-Exp
DeepSeek
A 685B (MoE) language model for chat and instruction-following.
EXAONE-3.5-32B-Instruct
LG AI Research
A 32B language model for chat and instruction-following.
GLM-4.5-Air
Z.ai (Zhipu)
A 110B (MoE) language model for chat and instruction-following.
GLM-4.6
Z.ai (Zhipu)
A 357B (MoE) language model for chat and instruction-following.
GLM-4.7-Flash
Z.ai (Zhipu)
A 31.2B (MoE) language model for chat and instruction-following.
GLM-5
Z.ai (Zhipu)
A 754B (MoE) language model for chat and instruction-following.
GLM-5.1
Z.ai (Zhipu)
A 754B (MoE) language model for chat and instruction-following.
GLM-5.2
Z.ai (Zhipu)
A 753B (MoE) language model for chat and instruction-following.
granite-3.2-8b-instruct
IBM
A 8.2B language model for chat and instruction-following.
Hermes-3-Llama-3.1-405B-FP8
Nous Research
A 406B language model for chat and instruction-following.
Hermes-3-Llama-3.1-70B
Nous Research
A 70.6B language model for chat and instruction-following.
Hermes-3-Llama-3.1-8B
Nous Research
A 8B language model for chat and instruction-following.
Kimi-K2-Instruct
Moonshot AI
A 1026B (MoE) language model for chat and instruction-following.
Kimi-K2-Instruct-0905
Moonshot AI
A 1026B (MoE) language model for chat and instruction-following.
Llama-3.1-405B-Instruct
Meta
A 406B language model for chat and instruction-following.
Meta-Llama-3.1-70B-Instruct-FP8
Red Hat AI
A 70.6B language model for chat and instruction-following.
Llama-3.1-8B-Instruct
Meta
A 8B language model for chat and instruction-following.
Llama-3.1-8B-Lexi-Uncensored-V2
Orenguteng (community)
A 8B language model for chat and instruction-following.
Llama-3.1-Nemotron-Nano-8B-v1
NVIDIA
A 8B language model for chat and instruction-following.
Llama-3.2-3B-Instruct
Meta
A 3.2B language model for chat and instruction-following.
Llama-Guard-3-8B
Meta
A 8B language model for chat and instruction-following.
Llama-Guard-4-12B
Meta
A 12B language model for chat and instruction-following.
MiniMax-H3
MiniMax
A 33.1B language model for chat and instruction-following.
MiniMax-M2.5
MiniMax
A 229B (MoE) language model for chat and instruction-following.
MiniMax-M2.7
MiniMax
A 229B (MoE) language model for chat and instruction-following.
Mistral-Small-24B-Instruct-2501
Mistral AI
A 23.6B language model for chat and instruction-following.
Mixtral-8x7B-Instruct-v0.1
Mistral AI
A 46.7B (MoE) language model for chat and instruction-following.
Nous-Hermes-2-Mistral-7B-DPO
Nous Research
A 7.2B language model for chat and instruction-following.
Phi-3.5-mini-instruct
Microsoft
A 3.8B language model for chat and instruction-following.
Phi-3-mini-4k-instruct
Microsoft
A 3.8B language model for chat and instruction-following.
phi-4
Microsoft
A 14.7B language model for chat and instruction-following.
Qwen2.5-14B-Instruct
Alibaba (Qwen)
A 14.8B language model for chat and instruction-following.
Qwen2.5-3B-Instruct
Alibaba (Qwen)
A 3.1B language model for chat and instruction-following.
Qwen3-1.7B
Alibaba (Qwen)
A 2B language model for chat and instruction-following.
Qwen3-1.7B-Base
Alibaba (Qwen)
A 1.7B language model for chat and instruction-following.
Qwen3-14B-Base
Alibaba (Qwen)
A 14.8B language model for chat and instruction-following.
Qwen3-235B-A22B-Instruct-2507-FP8
Alibaba (Qwen)
A 235B (MoE) language model for chat and instruction-following.
Qwen3-30B-A3B
Alibaba (Qwen)
A 30.5B (MoE) language model for chat and instruction-following.
Qwen3-32B
Alibaba (Qwen)
A 32.8B language model for chat and instruction-following.
Qwen3-4B
Alibaba (Qwen)
A 4B language model for chat and instruction-following.
Qwen3-4B-Base
Alibaba (Qwen)
A 4B language model for chat and instruction-following.
Qwen3.5-122B-A10B
Alibaba (Qwen)
A 125B (MoE) language model for chat and instruction-following.
Qwen3.5-397B-A17B
Alibaba (Qwen)
A 403B (MoE) language model for chat and instruction-following.
Qwen3.5-9B
Alibaba (Qwen)
A 9.7B language model for chat and instruction-following.
Qwen3.6-35B-A3B
Alibaba (Qwen)
A 36B (MoE) language model for chat and instruction-following.
Qwen3.8-27B-FP8
Alibaba (Qwen)
A 27.8B language model for chat and instruction-following.
Qwen3-8B
Alibaba (Qwen)
A 8.2B language model for chat and instruction-following.
ReaderLM-v2
Jina AI
A 1.5B language model for chat and instruction-following.
SmolLM2-360M-Instruct
Hugging Face
A 362M language model for chat and instruction-following.
Trinity-Large-Preview
Arcee AI
A 399B (MoE) language model for chat and instruction-following.
Wayfarer-12B
Latitude Games
A 12.2B language model for chat and instruction-following.
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
NVIDIA
A 550B (MoE) language model for chat and agentic tool use.
Reasoning
DeepSeek-R1-0528
DeepSeek
A 685B-parameter reasoning model tuned for math, coding and multi-step logic.
DeepSeek-R1-Distill-Llama-70B
DeepSeek
A 70.6B model tuned to reason step by step before answering.
DeepSeek-R1-Distill-Llama-8B-abliterated
huihui-ai (community)
A 8B model tuned to reason step by step before answering.
DeepSeek-R1-Distill-Qwen-1.5B
DeepSeek
A 1.8B model tuned to reason step by step before answering.
DeepSeek-R1-Distill-Qwen-14B-abliterated-v2
huihui-ai (community)
A 14.8B model tuned to reason step by step before answering.
Dolphin3.0-R1-Mistral-24B
Cognitive Computations (Dolphin)
A 23.6B model tuned to reason step by step before answering.
Qwen3-235B-A22B-Thinking-2507
Alibaba (Qwen)
A 235B (MoE) model tuned to reason step by step before answering.
Qwen3-Next-80B-A3B-Instruct
Alibaba (Qwen)
A 81.3B (MoE) model tuned to reason step by step before answering.
Qwen3-Next-80B-A3B-Thinking
Alibaba (Qwen)
A 81.3B (MoE) model tuned to reason step by step before answering.
gpt-oss-120b
OpenAI
A 117B (MoE) reasoning model whose MXFP4 weights fit a single 80GB GPU.
gpt-oss-20b
OpenAI
A 21B (MoE) reasoning model whose MXFP4 weights run within 16GB.
DeepSeek-V4-Pro-0813
DeepSeek
A 1.6T-parameter (49B active) reasoning model with a 1M-token context.
DeepSeek-V4-Flash-0731
DeepSeek
A 284B-parameter (13B active) reasoning model with a 1M-token context.
Coding
deepseek-coder-6.7b-instruct
DeepSeek
A 6.7B model tuned for code generation.
Qwen2.5-Coder-32B-Instruct
Alibaba (Qwen)
A 32.8B model tuned for code generation.
Qwen3-Coder-480B-A35B-Instruct
Alibaba (Qwen)
A 480B (MoE) model tuned for code generation.
Qwen3-Coder-Next
Alibaba (Qwen)
A 79.7B (MoE) model tuned for code generation.
MiniMax-M2
MiniMax AI
A 230B (MoE) model built for coding and agentic tool-use workflows.
Vision
DeepSeek-OCR
DeepSeek
A 3.3B (MoE) vision-language model that reads images alongside text.
gemma-3-12b-it
A 12.2B vision-language model that reads images alongside text.
gemma-3-4b-it
A 4.3B vision-language model that reads images alongside text.
gemma-4-31B-it
A 31.3B vision-language model that reads images alongside text.
GLM-4.5V
Z.ai (Zhipu)
A 108B vision-language model that reads images alongside text.
InternVL3-78B
OpenGVLab (Shanghai AI Lab)
A 78.4B vision-language model that reads images alongside text.
Llama-4-Maverick-17B-128E-Instruct-FP8
Meta
A 402B (MoE) vision-language model that reads images alongside text.
Llama-4-Scout-17B-16E-Instruct
Meta
A 109B (MoE) vision-language model that reads images alongside text.
Nanonets-OCR-s
Nanonets
A 3.8B vision-language model that reads images alongside text.
Qwen3-VL-32B-Instruct
Alibaba (Qwen)
A 33.4B vision-language model that reads images alongside text.
Kimi K2.5
Moonshot AI
A 1T-parameter (32B active) native multimodal agentic model.
gemma-4-12B-it
A 12.0B vision-language model that reads images alongside text.
gemma-4-26B-A4B-it
A 25.8B vision-language model that reads images alongside text.
gemma-4-E4B-it
An 8.0B vision-language model that reads images alongside text.
gemma-4-E2B-it
A 5.1B vision-language model that reads images alongside text.
Image generation
FLUX.1 [dev]
Black Forest Labs
A 12B-parameter rectified-flow transformer for text-to-image generation.
FLUX.1-Kontext-dev
Black Forest Labs
A 11.9B-parameter text-to-image model.
FLUX.1-schnell
Black Forest Labs
A 11.9B-parameter text-to-image model.
FLUX.2-dev
Black Forest Labs
A 32.2B-parameter text-to-image model.
HiDream-I1-Full
HiDream
A 17.1B-parameter text-to-image model.
Krea-2-Raw
Krea AI
A 12.8B-parameter text-to-image model.
Qwen-Image
Alibaba (Qwen)
A 20.4B-parameter text-to-image model.
RealVisXL_V5.0
Independent (SG161222)
A 2.6B-parameter text-to-image model.
stable-diffusion-xl-base-1.0
Stability AI
A 2.6B-parameter text-to-image model.
Video generation
LTX-2
Lightricks
A 18.9B-parameter video generation model.
mochi-1-preview
Genmo
A 10B-parameter video generation model.
Wan2.2-T2V-A14B
Wan-AI (Alibaba)
A 14.3B-parameter text-to-video MoE diffusion model.
Wan2.2-I2V-A14B
Wan-AI (Alibaba)
A 14.3B-parameter image-to-video MoE diffusion model.
Wan2.2-TI2V-5B
Wan-AI (Alibaba)
A 5B-parameter text/image-to-video model that runs on a consumer 4090.
