Model comparison

Qwen3-VL-8B-Instruct-Minecraft-MT-en-zh vs HyperCLOVAX-SEED-Text-Instruct-1.5B

These two publish different quantization sets; the table below has the exact sizes.

From the file· summed bytes, KV per layer

Side by side

Qwen3-VL-8B-Instruct-Minecraft-MT-en-zhHyperCLOVAX-SEED-Text-Instruct-1.5B
Parameters8.8B1.6B
Architectureqwen3vlllama
Layers36
Native context262,144
Mixture of expertsnono
Quantizations published241
Smallest quantization1.97 GiB1.06 GiB
Q4_K_M1.06 GiB
Licencecc-by-nc-sa-4.0other

KV cache by context

the term that decides long-context viability
ContextQwen3-VL-8B-Instruct-Minecraft-MT-en-zhHyperCLOVAX-SEED-Text-Instruct-1.5BRatio
4,0960.56 GiB
8,1921.13 GiB
16,3842.25 GiB
32,7684.50 GiB
65,5369.00 GiB
131,07218.00 GiB