vram.run Models Hardware Providers Cloud State of Inference
API provider data is live · Hardware & cloud pricing curated 2026-02-23

Nscale

24 live models

Models

ModelTaskParams
stable-diffusion-xl-base-1.0text-to-image
Llama-3.1-8B-Instructtext-generation
FLUX.1-schnelltext-to-image
gpt-oss-120btext-generation120B
gpt-oss-20btext-generation21.5B
QwQ-32Btext-generation
Llama-3.3-70B-Instructtext-generation
Qwen2.5-Coder-32B-Instructtext-generation32.8B
DeepSeek-R1-Distill-Qwen-32Btext-generation32.8B
DeepSeek-R1-Distill-Qwen-1.5Btext-generation
Llama-4-Scout-17B-16E-Instructimage-text-to-text109B
Qwen3-235B-A22Btext-generation235B
Qwen3-8Btext-generation
DeepSeek-R1-Distill-Llama-8Btext-generation
DeepSeek-R1-Distill-Qwen-7Btext-generation7.6B
Qwen3-4B-Instruct-2507text-generation
Qwen3-235B-A22B-Instruct-2507text-generation
DeepSeek-R1-Distill-Llama-70Btext-generation
Mixtral-8x22B-Instruct-v0.1141B
Qwen3-32Btext-generation
Qwen2.5-Coder-7B-Instructtext-generation7.6B
Qwen3-4B-Thinking-2507text-generation
Qwen3-14Btext-generation
Qwen2.5-Coder-3B-Instructtext-generation3.1B
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0