Edit Models filters

Model Tree

Apps

Docker Model Runner

Inference Providers

OVHcloud AI Endpoints

HF Inference API

One-click Deployment

Inference Endpoints

Microsoft Foundry

Amazon SageMaker AI

Misc

low-bit-open-llm-leaderboard

text-generation-inference

Eval Results (legacy)

text-embeddings-inference

4-bit precision

8-bit precision

Mixture of Experts

Carbon Emissions

Models

170

Base only

Active filters: low-bit-open-llm-leaderboard

LeaderboardModel1/LFM2.5-1.2B-Thinking-CodeX-AutoRound-W4A16-RTN

Text Generation • 0.3B • Updated May 27 • 14 • 1

LeaderboardModel1/gemma-4-12B-AutoRound-W4A16-RTN

Text Generation • 1B • Updated Jul 9 • 395 • 2

LeaderboardModel1/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-AutoRound-W4A16-RTN

Text Generation • 0.5B • Updated Jul 18 • 18 • 1

LeaderboardModel1/HRM-Text-1B-autoround-W4A16

Text Generation • 0.3B • Updated May 21 • 9

LeaderboardModel1/zeta-2.1-autoround-W4A16

Text Generation • 2B • Updated May 21 • 880

LeaderboardModel1/gemma-4-E4B-it-OBLITERATED-autoround-W4A16

Text Generation • Updated May 21 • 1

LeaderboardModel1/Seed-Coder-8B-Base-autoround-W4A16

Text Generation • 2B • Updated May 21 • 8

LeaderboardModel1/HRM-Text-1B-autoround-MXFP4

Text Generation • 1B • Updated May 21 • 11

LeaderboardModel1/Nandi-Mini-150M-Tool-Calling-autoround-W4A16

Text Generation • 47.9M • Updated May 21 • 10

LeaderboardModel1/Laguna-XS.2-autoround-W4A16

Text Generation • 5B • Updated May 21 • 23

LeaderboardModel1/Qwen3.6-35B-A3B-autoround-W4A16

Text Generation • 6B • Updated May 21 • 47

LeaderboardModel1/GLM-OCR-autoround-W4A16

Text Generation • 0.7B • Updated May 21 • 157

LeaderboardModel1/Nandi-Mini-600M-Early-Checkpoint-autoround-W4A16

Text Generation • 0.6B • Updated May 21 • 11

LeaderboardModel1/Qwen3.5-0.8B-Base-autoround-W4A16

Text Generation • Updated May 23

LeaderboardModel1/Qwen3.5-0.8B-Base-autoround-NVFP4

Text Generation • 0.8B • Updated May 23 • 11

LeaderboardModel1/Qwen3.6-27B-DFlash-autoround-W4A16

Text Generation • 3B • Updated May 23 • 92 • 2

LeaderboardModel1/Qwen3.5-0.8B-Base-autoround-MXFP4

Text Generation • 0.8B • Updated May 23 • 12

LeaderboardModel1/Qwen3-32B-autoround-W4A16

Text Generation • 6B • Updated May 25 • 15

LeaderboardModel1/Qwen3.5-0.8B-autoround-MXFP4

Text Generation • 0.8B • Updated May 25 • 18

LeaderboardModel1/Qwen3.5-0.8B-autoround-NVFP4

Text Generation • 0.8B • Updated May 25 • 12

LeaderboardModel1/Qwen3-4B-autoround-MXFP4

Text Generation • 4B • Updated May 25 • 11

LeaderboardModel1/Qwen3.5-2B-autoround-MXFP4

Text Generation • 2B • Updated May 25 • 11

LeaderboardModel1/Qwen3.5-2B-autoround-NVFP4

Text Generation • 2B • Updated May 25 • 14

LeaderboardModel1/MiMo-V2.5-ASR-AutoRound-W4A16-RTN

Text Generation • 2B • Updated May 25 • 13

LeaderboardModel1/Hy-MT2-7B-AutoRound-W4A16-RTN

Text Generation • 1B • Updated May 27 • 11

LeaderboardModel1/gemma-4-A4B-98e-v6-coder-it-AutoRound-MXFP4-RTN

Text Generation • 2B • Updated Jun 1 • 10

LeaderboardModel1/Kimi-Linear-48B-A3B-Instruct-AutoRound-W4A16-RTN

Text Generation • 7B • Updated May 27 • 10

LeaderboardModel1/LFM2.5-1.2B-Distilled-Claude-4.6-AutoRound-W4A16-RTN

Text Generation • 0.3B • Updated May 27 • 13

LeaderboardModel1/gpt2-AutoRound-W4A16-RTN

Text Generation • 50.9M • Updated May 27 • 8

LeaderboardModel1/Qwen3-0.6B-AutoRound-W4A16-RTN

Text Generation • 0.2B • Updated May 28 • 9