Skip to main content

Models

What you can run on Pie depends on three choices: the model architecture, the driver Pie routes inference through, and the precision and parallelism that driver supports for that architecture. This page is the at-a-glance matrix. For configuration and supported architectures of each driver, see CUDA.

Drivers

cuda

Standalone C++/CUDA binary for high-throughput inference.

Hardware
SM 8.0+
Weights
bf16int8int4
Parallel
TPDPPP

Architecture support

stable tested end-to-end preview implemented, not yet verified upstream covered by upstream backend not supported
ArchitecturecudavllmsglangtrtllmCheckpoints
Qwen
Qwen 2qwen2stableupstreamupstream
Qwen 2.5qwen2stableupstreamupstream
Qwen 3qwen3stableupstreamupstreamupstream
Qwen 3 MoEqwen3_moepreviewupstreamupstream
Qwen 3.5qwen3_5stableupstreamupstream
Qwen 3.5 MoEqwen3_5_moeupstream
Qwen 3.6qwen3_5stableupstreamupstream
Qwen 3.6 MoEqwen3_5_moeupstream
Qwen3-VLqwen3_vlstableupstreamupstream
Llama
Llama 3llamastableupstreamupstream
Llama 3.1llamastableupstreamupstream
Llama 3.2llamastableupstreamupstream
Gemma
Gemma 2gemma2stableupstreamupstream
Gemma 3gemma3, gemma3_textstableupstreamupstream
Gemma 3ngemma3n, gemma3n_textupstreamupstream
Gemma 4gemma4, gemma4_textstableupstream
Gemma 4 MoEgemma4 (with experts)
GPT-OSS
GPT-OSSgpt_oss, gptossstableupstreamupstream
Mistral
Mistralmistralupstreamupstream
Ministral 3mistral3stableupstream
Mistral Smallmistral3stableupstreamupstream
Mixtralmixtralstableupstreamupstream
Phi
Phi-3phi3stableupstreamupstream
Phi-3-smallphi3smallupstreamupstream
Phi-3.5 / Phi-4phi3stableupstreamupstream
Phi-3.5-MoEphimoeupstreamupstream
OLMo
OLMo 2olmo2upstreamupstream
OLMo 3olmo3stableupstreamupstream
GLM
GLM-5.1glm_moe_dsapreviewupstreamupstream
Nemotron
Nemotron-Hnemotron_hstable
DeepSeek / Kimi
DeepSeek V3deepseek_v3previewupstreamupstream
Kimi K2kimi_k2previewupstreamupstream
Sesame
CSMcsmpreview

Multimodal models. Qwen3-VL (vision), Gemma 4 (vision + audio), Nemotron-3 Omni (vision + audio), and CSM (audio output) accept or produce non-text modalities. See Multimodal generation.