Spaces:

Intel
/

low_bit_open_llm_leaderboard

Running

App Files Files Community

Resources

View closed (15)

microsoft/Fara1.5-4B | MXFP8

#43 opened 3 days ago by

ProCreations/grug-27b | INT4 (W4A16)

#42 opened 8 days ago by

google/gemma-4-E2B-it-qat-q4_0-unquantized-assistant | INT4 (W4A16)

#41 opened 13 days ago by

Quazim0t0/Escarda-86M-Base | W4A16

#40 opened 17 days ago by

bottlecapai/ThinkingCap-Qwen3.6-27B | INT4 (W4A16)

#39 opened 18 days ago by

Qwen/Qwen3.5-35B-A3B | INT4 (W4A16)

#38 opened 21 days ago by

Quazim0t0/Escarda-86M-Base | INT4 (W4A16)

#37 opened 24 days ago by

Quazim0t0/Escarda-86M-Base | INT4 (W4A16)

#36 opened 24 days ago by

FlameF0X/LFM2.5-1.2B-Distilled-Claude | INT4 (W4A16)

#32 opened 30 days ago by

google/gemma-4-12B-IT | INT4 (W4A16)

#27 opened about 1 month ago by

empero-ai/Qwen3.5-9B-Claude-Opus-4.6-Distill | INT4 (W4A16)

#26 opened about 1 month ago by

Quazim0t0/Escarda-86M-Base | MXFP4

#19 opened about 1 month ago by

Quazim0t0/Escarda-86M-Base | INT4 (W4A16)

#18 opened about 1 month ago by

Space Notifications

#11 opened about 1 month ago by

GLM 5.2

#9 opened about 1 month ago by

My models failed

#8 opened about 1 month ago by

Cost-per-token benchmarking tool to complement quantized model accuracy tracking

#7 opened about 2 months ago by

Features (TODO)

#6 opened 2 months ago by

details

#2 opened about 2 years ago by