Model comparison

Qwen2.5-VL-7B-Abliterated-Caption-it vs Llama-3.1-8B-Instruct

At Q4_K_M, Qwen2.5-VL-7B-Abliterated-Caption-it is the smaller download — 1,929,902,080 bytes against 4,920,739,168.

From the file· summed bytes, KV per layer

Side by side

Qwen2.5-VL-7B-Abliterated-Caption-itLlama-3.1-8B-Instruct
Parameters8.3B8.0B
Architectureqwen2vlllama
Layers32
Native context131,072
Mixture of expertsnono
Quantizations published6045
Smallest quantization1.19 GiB2.02 GiB
Q4_K_M1.80 GiB4.58 GiB
Licenceapache-2.0llama3.1

KV cache by context

the term that decides long-context viability
ContextQwen2.5-VL-7B-Abliterated-Caption-itLlama-3.1-8B-InstructRatio
4,0960.50 GiB
8,1921.00 GiB
16,3842.00 GiB
32,7684.00 GiB
65,5368.00 GiB
131,07216.00 GiB