LLM Benchmarks

← Back to Models

hammer2.1-7b

hammer2.1-7b

Publisher

Nekuromento

Architecture

qwen2

Parameters

7B

Quantization

Q8_0 (8.0 bpw)

Format

gguf

Max Context

33k tokens

Type

llm

File Size

7.54 GB

Est. RAM

9.0 GB

Est. VRAM

9.0 GB

Benchmark Results