publisher

nvidia

0 builds measured across 22 families, and 13 derivatives of other people's models. Ranked by what machines proved, never by downloads.

derivatives — changes this publisher made to someone else's weightsDeepSeek-V3.1-NVFP4deepseek-v3-1DeepSeek-V3.2-NVFP4deepseek-v3-2diffusiongemma-26B-A4B-it-NVFP4diffusiongemmaGLM-5-NVFP4glm-5gpt-oss-120b-Eagle3-short-contextgpt-ossKimi-K2-Thinking-Eagle3kimi-k2Kimi-K2.5-Thinking-Eagle3kimi-k2-5Kimi-K2.6-DFlashkimi-k2-6Kimi-K2.6-Eagle3kimi-k2-6Kimi-K2.7-Code-DFlashkimi-k2-7MiniMax-M2.7-DFlashminimax-m2-7MiniMax-M3-DSparkminimax-m3Muse-Spark-Open-816B-A42B-DFlash2muse-spark
in the catalog, not yet measured — declared, unsignednvidia/DeepSeek-V3.1-NVFP4deepseek-v3-1/base~nvidia · BF16 · vllm · derivativenvidia/DeepSeek-V3.2-NVFP4deepseek-v3-2/base~nvidia · BF16 · vllm · derivativenvidia/diffusiongemma-26B-A4B-it-NVFP4diffusiongemma/26b-a4b~nvidia · NVFP4 · vllm · derivativenvidia/Gemma-4-26B-A4B-NVFP4gemma-4/26b-a4b · NVFP4 · vllm · quantizernvidia/Gemma-4-31B-IT-NVFP4gemma-4/31b · NVFP4 · vllm · quantizernvidia/GLM-5-NVFP4glm-5/base~nvidia · BF16 · vllm · derivativenvidia/GLM-5.1-NVFP4glm-5-1/base · NVFP4 · vllm · quantizernvidia/GLM-5.2-NVFP4glm-5-2/base · NVFP4 · vllm · quantizernvidia/GLM-5.3-Flash-NVFP4glm-5-3/flash · NVFP4 · vllm · quantizernvidia/gpt-oss-120b-Eagle3-short-contextgpt-oss/120b~nvidia-eagle3-short-context · BF16 · vllm · derivativenvidia/Kimi-K2-Thinking-NVFP4kimi-k2/thinking · NVFP4 · vllm · quantizernvidia/Kimi-K2-Thinking-Eagle3kimi-k2/thinking~nvidia-eagle3 · BF16 · vllm · derivativenvidia/Kimi-K2.5-NVFP4kimi-k2-5/base · NVFP4 · vllm · quantizernvidia/Kimi-K2.5-Thinking-Eagle3kimi-k2-5/base~nvidia-thinking-eagle3 · BF16 · vllm · derivativenvidia/Kimi-K2.6-NVFP4kimi-k2-6/base · NVFP4 · vllm · quantizernvidia/Kimi-K2.6-DFlashkimi-k2-6/base~nvidia-dflash · BF16 · vllm · derivativenvidia/Kimi-K2.6-Eagle3kimi-k2-6/base~nvidia-eagle3 · BF16 · vllm · derivativenvidia/Kimi-K2.7-Code-NVFP4kimi-k2-7/code · NVFP4 · vllm · quantizernvidia/Kimi-K2.7-Code-DFlashkimi-k2-7/code~nvidia-dflash · BF16 · vllm · derivativenvidia/Kimi-K3-NVFP4kimi-k3/base · MODELOPT_MIXED · vllm · quantizernvidia/MiniMax-M2.5-NVFP4minimax-m2-5/base · NVFP4 · vllm · quantizernvidia/MiniMax-M2.7-DFlashminimax-m2-7/base~nvidia-dflash · BF16 · vllm · derivativenvidia/MiniMax-M3-NVFP4minimax-m3/base · NVFP4 · vllm · quantizernvidia/MiniMax-M3-DSparkminimax-m3/base~nvidia-dspark · FP32 · vllm · derivativenvidia/Mistral-Medium-3.5-128B-NVFP4mistral-medium-3-5/128b · NVFP4 · vllm · quantizernvidia/Muse-Glimmer-30B-NVFP4muse-glimmer/30b · NVFP4 · vllm · quantizernvidia/Muse-Spark-Open-816B-A42B-DFlash2muse-spark/816b-a42b~nvidia-open-dflash2 · BF16 · vllm · derivativenvidia/Qwen3.5-122B-A10B-NVFP4qwen-3-5/122b-a10b · NVFP4 · vllm · quantizernvidia/Qwen3.6-27B-NVFP4qwen-3-6/27b · NVFP4 · vllm · quantizernvidia/Qwen3.6-35B-A3B-NVFP4qwen-3-6/35b-a3b · NVFP4 · vllm · quantizer