Inference Providers
Active filters: pruning
NexVeridian/Qwen3-Coder-REAP-25B-A3B-8bit
Text Generation
• 25B • Updated • 135
• 1
NexVeridian/Kimi-Linear-REAP-35B-A3B-Instruct-4bit
Text Generation
• 35B • Updated • 107
NexVeridian/Kimi-Linear-REAP-35B-A3B-Instruct-8bit
Text Generation
• 35B • Updated • 103
DarqueDante/gemma3-270m-pruned-base-Q4_0-GGUF
Text Generation
• 0.3B • Updated • 20
CrystalRaindropsFall/llava-heads-30pct
Image-to-Text
• 6B • Updated • 1
CrystalRaindropsFall/llava-glu-70pct
Image-to-Text
• 4B • Updated • 1
CrystalRaindropsFall/llava-heads-70pct
Image-to-Text
• 6B • Updated • 1
CrystalRaindropsFall/llava-glu-30pct
Image-to-Text
• 6B • Updated • 1
CrystalRaindropsFall/llava-l1-30pct
Image-to-Text
• 7B • Updated • 1
CrystalRaindropsFall/llava-l1-70pct
Image-to-Text
• 7B • Updated • 3
• 1
CrystalRaindropsFall/llava-glu30-heads30
Image-to-Text
• 5B • Updated • 2
CrystalRaindropsFall/llava-glu70-heads70
Image-to-Text
• 2B • Updated • 1
cerebras/DeepSeek-V3.2-REAP-345B-A37B
Text Generation
• 345B • Updated • 1.04k
• 34
cerebras/DeepSeek-V3.2-REAP-508B-A37B
Text Generation
• 508B • Updated • 25
• 16
Text Generation
• Updated • 6
epfl-ml-ytf/apertus-8b-pruned-latin-94237
8B • Updated • 7
AfriNLP/AfriNLLB-12enc-8dec-middle-548m-ft
Translation
• 0.5B • Updated • 6
naveedashfaq/llama-3-8b-pruned-30-percent
6B • Updated • 4
naveedashfaq/llama-3-8b-pruned-30-percent-taylor
6B • Updated • 3
• 1
epfl-ml-ytf/apertus-8b-pruned-eng-66663
8B • Updated • 7
AfriNLP/AfriNLLB-8enc-8dec-middle-498m-ft
Translation
• 0.5B • Updated • 12
avtc/GLM-4.6-REAP-268B-A32B-GPTQMODEL-W4A16-V2
Text Generation
• 271B • Updated • 7
epfl-ml-ytf/apertus-8b-pruned-english-ds-63159
7B • Updated • 9
dnaymont15/Qwen3-Coder-REAP-25B-A3B-Q3_K_S-GGUF
Text Generation
• 25B • Updated • 15
dnaymont15/Qwen3-Coder-REAP-25B-A3B-Q4_K_M-GGUF
Text Generation
• 25B • Updated • 6
dnaymont15/Qwen3-Coder-REAP-25B-A3B-Q3_K_L-GGUF
Text Generation
• 25B • Updated • 7
muchad/deberta-hybrid-7030-30k
0.1B • Updated • 5
muchad/deberta-single-30k
0.1B • Updated • 2
muchad/deberta-single-20k
0.1B • Updated • 5
Echoes123-3/qwen2.5-0.5b-coding-pruned
0.5B • Updated • 8