>>

Run any open model on Lium

Today's trending open models, with the VRAM each needs and the cheapest GPU setup that runs it right now. Pick one, rent the GPUs in seconds, pay per second.
ModelParametersVRAM neededCheapest setupPer hour
Qwen3.8-27B
Alibaba Qwen · Vision and text
27.8B67 GBA100 80GB PCIefrom $0.81Rent
Kimi-K3.1-Pro
Moonshot AI · Vision and text
2.8T1874 GB8x B300 SXM6from $32.00Rent
DeepSeek-V4.1-Flash-1017
DeepSeek · Vision and text
763.2B613 GB8x RTX PRO 6000 Workstationfrom $15.92Rent
Meta-Llama-3-8B-Instruct
Meta · Text generation
8B20 GBRTX 3090from $0.16Rent
Qwen3.8-Flash-Next
Alibaba Qwen · Vision and text
180B432 GB8x RTX PRO 6000 Workstationfrom $15.92Rent
LFM3-1.7B
Liquid AI · Text generation
1.7B5 GBGTX 1660 Tifrom $0.10Rent
LFM3-Omni-2B
Liquid AI · Multimodal
2.2B6 GBGTX 1660 Tifrom $0.10Rent
GLM-5.3-Flash
Z.ai · Vision and text
321.3B394 GB8x RTX PRO 6000 Workstationfrom $15.92Rent
MiniMax-H3-Image-PE
MiniMax · Text generation
27.4B22 GBRTX 3090from $0.16Rent
flux-3-image-klein
Black Forest Labs · Image editing
5.5B25 GB2x RTX 5060 Tifrom $0.30Rent
Qwen3.8-27B-DSpine-b16
Tencent · Text generation
2B5 GBGTX 1660 Tifrom $0.10Rent
FLUX.1-dev
Black Forest Labs · Image generation
11.9B41 GB2x RTX 3090from $0.36Rent
FLUX.1-schnell
Black Forest Labs · Image generation
11.9B41 GB2x RTX 3090from $0.36Rent
Llama-3.1-8B-Instruct
Meta · Text generation
8B20 GBRTX 3090from $0.16Rent
GLM-5.3
Z.ai · Text generation
753.3B907 GB8x H200from $28.00Rent
Qwen-Image-2.1
Alibaba Qwen · Image generation
7.1B40 GB2x RTX 3090from $0.36Rent
d1-2B
Liquid AI · Vision and text
1.9B5 GBGTX 1660 Tifrom $0.10Rent
gemma-4-31B-it
Google · Vision and text
31.3B75 GBA100 80GB PCIefrom $0.81Rent
Kimi-K3
Moonshot AI · Vision and text
2.8T1874 GB8x B300 SXM6from $32.00Rent
Qwen3.5-9B
Alibaba Qwen · Vision and text
9.7B24 GBRTX 3090from $0.16Rent
MiniMax-M3.1-Flash
MiniMax · Vision and text
220.5B301 GB8x RTX A6000from $3.20Rent
FLUX.2-dev
Black Forest Labs · Image editing
32.2B136 GB4x RTX A6000from $1.60Rent
Llama-3.2-3B-Instruct
Meta · Text generation
3.2B8 GBRTX 4060 Tifrom $0.14Rent
NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB
NVIDIA · Vision and text
24.6B29 GB2x RTX 5060 Tifrom $0.30Rent
Qwen3.6-35B-A3B
Alibaba Qwen · Vision and text
36B87 GB2x RTX A6000from $0.84Rent
Qwen3.5-4B
Alibaba Qwen · Vision and text
4.7B12 GBRTX 5060 Tifrom $0.15Rent
LFM3-Audio-2B
Liquid AI · Multimodal
2B5 GBGTX 1660 Tifrom $0.10Rent
gpt-oss-120b
OpenAI · Text generation
116.8B79 GBA100 80GB PCIefrom $0.81Rent
FLUX.2-klein-9B
Black Forest Labs · Image editing
9.1B42 GB2x RTX 3090from $0.36Rent
gemma-4-26B-A4B-it
Google · Vision and text
25.8B62 GBA100 80GB PCIefrom $0.81Rent
Qwen3.5-0.8B
Alibaba Qwen · Vision and text
0.9B3 GBGTX 1660 Tifrom $0.10Rent
medgemma-1.5-4b-it
Google · Vision and text
4.3B11 GBRTX 5060 Tifrom $0.15Rent
Llama-3.1-8B
Meta · Text generation
8B20 GBRTX 3090from $0.16Rent
granite-4.1-8b-llmon-preview
IBM · Text generation
8.8B22 GBRTX 3090from $0.16Rent
paligemma-3b-pt-224
Google · Vision and text
2.9B15 GBRTX 5060 Tifrom $0.15Rent
granite-4.1-3b-llmon-preview
IBM · Text generation
3.7B9 GBRTX 5060 Tifrom $0.15Rent
Qwen3.8-2.4T-A95B
Alibaba Qwen · Text generation
2.4T5871 GBA multi-node cluster-Request
gpt-oss-20b
OpenAI · Text generation
20.9B17 GBRTX 3090from $0.16Rent
gemma-3-4b-it
Google · Vision and text
4.3B11 GBRTX 5060 Tifrom $0.15Rent
gemma-4-E2B-it
Google · Multimodal
5.1B13 GBRTX 5060 Tifrom $0.15Rent
gemma-4-12B
Google · Multimodal
12B29 GB2x RTX 5060 Tifrom $0.30Rent
Qwen3-0.6B
Alibaba Qwen · Text generation
0.8B2 GBGTX 1660 Tifrom $0.10Rent
WeVisOne-VL-4B
Tencent · Vision and text
4.8B12 GBRTX 5060 Tifrom $0.15Rent
FLUX.2-klein-4B
Black Forest Labs · Image editing
3.9B20 GBRTX 3090from $0.16Rent
LFM3-VL-2B
Liquid AI · Vision and text
1.9B5 GBGTX 1660 Tifrom $0.10Rent
Cosmos-Reason2-2B
NVIDIA · Vision and text
2.4B6 GBGTX 1660 Tifrom $0.10Rent
Qwen3-Coder-30B-A3B-Instruct
Alibaba Qwen · Text generation
30.5B74 GBA100 80GB PCIefrom $0.81Rent
Meta-Llama-3-8B
Meta · Text generation
8B20 GBRTX 3090from $0.16Rent
Llama-3.2-3B
Meta · Text generation
3.2B8 GBRTX 4060 Tifrom $0.14Rent
MiMo-V2.6-Distill-Qwen-9B
Xiaomi · Vision and text
9.4B23 GBRTX 3090from $0.16Rent
Hy4-preview
Tencent · Text generation
780B1872 GB8x B300 SXM6from $32.00Rent
medgemma-4b-it
Google · Vision and text
4.3B11 GBRTX 5060 Tifrom $0.15Rent
LFM2.5-24B-A2B
Liquid AI · Text generation
24B58 GBA100 80GB PCIefrom $0.81Rent
Llama-3.2-1B
Meta · Text generation
1.2B3 GBGTX 1660 Tifrom $0.10Rent
Ling-3.0-tiny
Ant Group · Text generation
7.9B19 GBRTX 3090from $0.16Rent
granite-4.2-8b
IBM · Text generation
8.8B22 GBRTX 3090from $0.16Rent
gemma-4-E4B-it
Google · Multimodal
8B20 GBRTX 3090from $0.16Rent
gemma-4-12B-it
Google · Multimodal
12B29 GB2x RTX 5060 Tifrom $0.30Rent
d1-3B
Liquid AI · Vision and text
3.1B8 GBRTX 4060 Tifrom $0.14Rent
MiMo-V2.6-Pro-RL
Xiaomi · Text generation
1T680 GB8x RTX PRO 6000 Workstationfrom $15.92Rent
DeepSeek-V4-Flash-0731
DeepSeek · Text generation
304.2B201 GB8x RTX A6000from $3.20Rent
DeepSeek-R1
DeepSeek · Text generation
684.5B827 GB8x H200from $28.00Rent
DeepSeek-R1-Distill-Qwen-7B
DeepSeek · Text generation
7.6B19 GBRTX 3090from $0.16Rent
Llama-3.3-70B-Instruct
Meta · Text generation
70.6B170 GB4x RTX A6000from $1.60Rent
Ling-3.1-flash
Ant Group · Text generation
572.1B689 GB8x RTX PRO 6000 Workstationfrom $15.92Rent
Llama-3.2-1B-Instruct
Meta · Text generation
1.2B3 GBGTX 1660 Tifrom $0.10Rent
MiMo-V2.6-Flash-RL
Xiaomi · Text generation
310.8B208 GB8x RTX A6000from $3.20Rent
FLUX.1-Kontext-dev
Black Forest Labs · Image editing
11.9B41 GB2x RTX 3090from $0.36Rent
Llama-2-7b-chat-hf
Meta · Text generation
6.7B17 GBRTX 3090from $0.16Rent
DeepSeek-V4-Pro-0813
DeepSeek · Text generation
1.7T1072 GB8x H200from $28.00Rent
DeepSeek-V3.2
DeepSeek · Text generation
685.4B828 GB8x H200from $28.00Rent
GLM-4.7-Flash
Z.ai · Text generation
31.2B75 GBA100 80GB PCIefrom $0.81Rent
MiniMax-M3
MiniMax · Vision and text
427B1026 GB8x H200from $28.00Rent
SingVL_S1_4B
Ant Group · Vision and text
4.5B11 GBRTX 5060 Tifrom $0.15Rent
HunyuanImage-3.0
Tencent · Image generation
83B203 GB8x RTX A6000from $3.20Rent
WeVisOne-VL-2B
Tencent · Vision and text
2.4B6 GBGTX 1660 Tifrom $0.10Rent
DeepSeek-R1-Distill-Qwen-1.5B
DeepSeek · Text generation
1.8B5 GBGTX 1660 Tifrom $0.10Rent
DeepSeek-V4-Flash-Vision-Exp
DeepSeek · Vision and text
304.6B202 GB8x RTX A6000from $3.20Rent
GLM-5.2
Z.ai · Text generation
753.3B1809 GB8x B300 SXM6from $32.00Rent
Llama-4-Maverick-17B-128E-Instruct
Meta · Vision and text
401.6B964 GB8x H200from $28.00Rent
deepseek-coder-6.7b-instruct
DeepSeek · Text generation
6.7B17 GBRTX 3090from $0.16Rent
DeepSeek-R1-0528-Qwen3-8B
DeepSeek · Text generation
8.2B20 GBRTX 3090from $0.16Rent
Kimi-Linear-48B-A3B-Instruct
Moonshot AI · Text generation
49.1B118 GB4x RTX A6000from $1.60Rent
Llama-3.1-405B
Meta · Text generation
405.9B975 GB8x H200from $28.00Rent
Llama-4-Scout-17B-16E-Instruct
Meta · Vision and text
108.6B261 GB8x RTX A6000from $3.20Rent
granite-4.2-3b
IBM · Text generation
3.7B9 GBRTX 5060 Tifrom $0.15Rent
granite-4.2-30b
IBM · Text generation
29.3B71 GBA100 80GB PCIefrom $0.81Rent
Kimi-VL-A3B-Thinking-2506
Moonshot AI · Vision and text
16.4B40 GB2x RTX 3090from $0.36Rent
Kimi-K2-Thinking
Moonshot AI · Text generation
1T714 GB8x RTX PRO 6000 Workstationfrom $15.92Rent
Kimi-K2.6
Moonshot AI · Vision and text
1T715 GB8x RTX PRO 6000 Workstationfrom $15.92Rent
Kimi-K2.7-Code
Moonshot AI · Vision and text
1T715 GB8x RTX PRO 6000 Workstationfrom $15.92Rent
MiniMax-M2.5
MiniMax · Text generation
228.7B277 GB8x RTX A6000from $3.20Rent
Mistral-7B-v0.1
Mistral AI · Text generation
7.2B18 GBRTX 3090from $0.16Rent
Molmo2-4B
Ai2 · Vision and text
4.9B24 GBRTX 3090from $0.16Rent
Ling-3.0-flash
Ant Group · Text generation
127.5B306 GB8x RTX A6000from $3.20Rent
granite-docling-258M
IBM · Vision and text
0.3B1 GBGTX 1660 Tifrom $0.10Rent
Moonlight-16B-A3B-Instruct
Moonshot AI · Text generation
16B39 GB2x RTX 3090from $0.36Rent
Kimi-VL-A3B-Instruct
Moonshot AI · Vision and text
16.4B40 GB2x RTX 3090from $0.36Rent
Kimi-Dev-72B
Moonshot AI · Text generation
72.7B175 GB4x RTX A6000from $1.60Rent
Kimi-K2.5
Moonshot AI · Vision and text
1T715 GB8x RTX PRO 6000 Workstationfrom $15.92Rent
codegeex4-all-9b
Z.ai · Text generation
9.4B23 GBRTX 3090from $0.16Rent
GLM-4.5-Air
Z.ai · Text generation
110.5B266 GB8x RTX A6000from $3.20Rent
GLM-4.6V-Flash
Z.ai · Vision and text
10.3B25 GB2x RTX 5060 Tifrom $0.30Rent
MiniMax-M2.7
MiniMax · Text generation
228.7B277 GB8x RTX A6000from $3.20Rent
OLMoE-1B-7B-0125
Ai2 · Text generation
6.9B34 GB2x RTX 3090from $0.36Rent
OLMo-2-0325-32B-Instruct
Ai2 · Text generation
32.2B78 GBA100 80GB PCIefrom $0.81Rent
Olmo-3-32B-Think
Ai2 · Text generation
32.2B78 GBA100 80GB PCIefrom $0.81Rent
Olmo-3-7B-Instruct
Ai2 · Text generation
7.3B18 GBRTX 3090from $0.16Rent
Olmo-3.1-32B-Think
Ai2 · Text generation
32.2B78 GBA100 80GB PCIefrom $0.81Rent
MiMo-Audio-7B-Instruct
Xiaomi · Multimodal
8B20 GBRTX 3090from $0.16Rent
MiMo-V2.6-Pro-MOPD
Xiaomi · Text generation
1T680 GB8x RTX PRO 6000 Workstationfrom $15.92Rent
MiMo-V2.6-Flash-MOPD
Xiaomi · Text generation
310.8B208 GB8x RTX A6000from $3.20Rent
granite-3.1-3b-a800m-instruct
IBM · Text generation
3.3B8 GBRTX 4060 Tifrom $0.14Rent
granite-3.3-2b-instruct
IBM · Text generation
2.5B7 GBRTX 4060 Tifrom $0.14Rent
Step-Audio-2-mini
StepFun · Multimodal
8.3B20 GBRTX 3090from $0.16Rent
ERNIE-Image-Turbo
Baidu · Image generation
8B38 GB2x RTX 3090from $0.36Rent
Moonlight-16B-A3B
Moonshot AI · Text generation
16B39 GB2x RTX 3090from $0.36Rent
MiniMax-Text-01
MiniMax · Text generation
456.1B1098 GB8x H200from $28.00Rent
MiniMax-VL-01
MiniMax · Vision and text
456.4B1099 GB8x H200from $28.00Rent
SynLogic-32B
MiniMax · Text generation
32.8B79 GBA100 80GB PCIefrom $0.81Rent
The list is the trending models from each lab's own Hugging Face account, refreshed every few hours. VRAM is the released weights plus about 20 % for activations and KV cache; long contexts and big batches need more.
For AI agents (CLI install, agent skill, headless signup): llms-full.txt