Model comparison

Darkmere-8B-v0.1 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

Darkmere-8B-v0.1HyperCLOVAX-SEED-Text-Instruct-1.5B
Parameters8.5B1.6B
Architecturemistral3llama
Layers
Native context
Mixture of expertsnono
Quantizations published241
Smallest quantization1.98 GiB1.06 GiB
Q4_K_M1.06 GiB
Licenceapache-2.0other

KV cache by context

the term that decides long-context viability
ContextDarkmere-8B-v0.1HyperCLOVAX-SEED-Text-Instruct-1.5BRatio
4,096
8,192
16,384
32,768
65,536
131,072