Labs & organizations

Qwen3-0.6B, Qwen3-8B, Qwen2.5-7B-Instruct

gpt2, gpt-oss-20b, gpt-oss-120b

gemma-3-1b-it, gemma-3-270m, gemma-3-270m-it

opt-125m, Llama-3.2-1B-Instruct, Llama-3.1-8B-Instruct

DeepSeek-R1, DeepSeek-V4-Flash, DeepSeek-V3.2

Claude 3 Opus, Claude 3 Sonnet, Claude 3.5 Haiku

Qwen3.6-35B-A3B-NVFP4, Gemma-4-26B-A4B-NVFP4, diffusiongemma-26B-A4B-it-NVFP4

Mistral-7B-Instruct-v0.2, Mistral-7B-v0.1, Magistral Small 1.1

Phi-3.5-mini-instruct, Phi-tiny-MoE-instruct, phi-4

GLM-4.7-Flash, GLM-5-FP8, GLM-5.2-FP8

Kimi-K2-Instruct-0905, Kimi K2 (Jul 2025), Kimi K2 (Sep 2025)

Grok 3, Grok 4, Grok 4 Fast

falcon-7b, Falcon 2 11B, Falcon-180B

SmolLM2-135M-Instruct, SmolLM2-135M, SmolLM3-3B

MiniMax-M2.7, MiniMax-M2.5, MiniMax-M2.5

Llama-3.2-1B-Instruct-FP8-dynamic, Qwen2.5-1.5B-quantized.w8a8, Llama-3.2-1B-Instruct-FP8

StarCoder 2 15B, StarCoder 2 3B, StarCoder 2 7B

Yi 6B, Yi-34B, Yi-9B

Baichuan 2-7B, Baichuan1-7B, Baichuan2-13B

pythia-160m, pythia-70m-deduped

PowerMoE-3b, granite-4.1-8b

h2ovl-mississippi-800m, h2ovl-mississippi-2b

MPT-30B, MPT-7B

Stable Beluga 2, stablelm-tuned-alpha-7b

internlm-20b, internlm-7b

OpenELM-1_1B-Instruct

Meta-Llama-3.1-8B-Instruct

Amazon Nova Pro

INTELLECT-1

RedPajama-INCITE-7B-Base

XGen-7B

open_llama_7b

vicuna-13b-v1.1

Dolly 2.0-12b

Cerebras-GPT-13B