Edit Models filters

Model Tree

winglian/llama-3-8b-256k-PoSE

Inference status

Misc

Inference Endpoints

AutoTrain Compatible

text-generation-inference

4-bit precision

text-embeddings-inference

8-bit precision

Carbon Emissions

Mixture of Experts

Models

6

Full-text search

Active filters: winglian/llama-3-8b-256k-PoSE

PrunaAI/winglian-llama-3-8b-256k-PoSE-HQQ-1bit-smashed

Text Generation • Updated Jul 12 • 10

PrunaAI/winglian-llama-3-8b-256k-PoSE-HQQ-2bit-smashed

Text Generation • Updated Jul 12 • 9

PrunaAI/winglian-llama-3-8b-256k-PoSE-QUANTO-int8bit-smashed

Updated Jul 19 • 1

PrunaAI/winglian-llama-3-8b-256k-PoSE-QUANTO-float8bit-smashed

Updated Jul 19 • 1

PrunaAI/winglian-llama-3-8b-256k-PoSE-QUANTO-int2bit-smashed

Updated Jul 19 • 2

PrunaAI/winglian-llama-3-8b-256k-PoSE-QUANTO-int4bit-smashed

Updated Jul 19 • 2