Model comparison

DeepSeek-R1-Distill-Qwen-1.5B vs HyperCLOVAX-SEED-Text-Instruct-1.5B

At Q4_K_M, DeepSeek-R1-Distill-Qwen-1.5B is the smaller download — 1,117,320,512 bytes against 1,133,974,368.

From the file· summed bytes, KV per layer

Side by side

DeepSeek-R1-Distill-Qwen-1.5BHyperCLOVAX-SEED-Text-Instruct-1.5B
Parameters1.8B1.6B
Architectureqwen2llama
Layers28
Native context131,072
Mixture of expertsnono
Quantizations published411
Smallest quantization0.65 GiB1.06 GiB
Q4_K_M1.04 GiB1.06 GiB
Licenceapache-2.0other

KV cache by context

the term that decides long-context viability
ContextDeepSeek-R1-Distill-Qwen-1.5BHyperCLOVAX-SEED-Text-Instruct-1.5BRatio
4,0960.11 GiB
8,1920.22 GiB
16,3840.44 GiB
32,7680.88 GiB
65,5361.75 GiB
131,0723.50 GiB
DeepSeek-R1-Distill-Qwen-1.5B vs HyperCLOVAX-SEED-Text-Instruct-1.5B — size, memory and hardware fit — ossmodeldb