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

Featherless vs Nscale

207 vs 19 models, 15 shared

Shared models

ModelFeatherless $/1M outFeatherless tok/sNscale $/1M outNscale tok/s
Qwen2.5-Coder-32B-Instruct47 tok/s
Qwen2.5-Coder-3B-Instruct174 tok/s
Qwen2.5-Coder-7B-Instruct150 tok/s
Qwen3-14B94 tok/s
Qwen3-235B-A22B14 tok/s
Qwen3-32B35 tok/s
Qwen3-4B-Instruct-2507150 tok/s
Qwen3-4B-Thinking-2507158 tok/s
Qwen3-8B133 tok/s
DeepSeek-R1-Distill-Llama-8B130 tok/s
DeepSeek-R1-Distill-Qwen-14B91 tok/s
DeepSeek-R1-Distill-Qwen-7B166 tok/s
Llama-3.1-8B-Instruct143 tok/s
gpt-oss-120b115 tok/s
gpt-oss-20b155 tok/s
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0