Model comparison

Qwen3.8-27B vs falcon-mamba-7b-instruct

At Q4_K_M, falcon-mamba-7b-instruct is the smaller download — 4,204,230,784 bytes against 16,810,714,336.

From the file· summed bytes, KV per layer

Side by side

Qwen3.8-27Bfalcon-mamba-7b-instruct
Parameters27.8B7.3B
Architectureqwen35mamba
Layers6464
Native context262,144
Mixture of expertsnono
Quantizations published221
Smallest quantization8.39 GiB3.92 GiB
Q4_K_M15.66 GiB3.92 GiB
Licenceapache-2.0other

KV cache by context

the term that decides long-context viability
ContextQwen3.8-27Bfalcon-mamba-7b-instructRatio
4,0960.25 GiB
8,1920.50 GiB
16,3841.00 GiB
32,7682.00 GiB
65,5364.00 GiB
131,0728.00 GiB