Model Terminal

kvc-scale8b-operators

A Hugging Face-hosted model repository providing KV-cache quantization operators for transformer inference, aimed at reducing memory usage and improving throughput when running large language models. It targets systems-level inference efficiency rather than serving as a standalone chat or application product. Source: supabase.

Value score
Not scored
Context
tokens
Max output
tokens
Price

Capability radar

Identity

Developer
ndsanjana
Openness
Modalities
Release
Knowledge cutoff
Deprecation
API docs

Benchmarks

No benchmark scores yet.

Compare nearby

Pricing

Input / 1M
Output / 1M
Speed