Model comparison

GLM-ASR-Nano-2512 vs cohere-transcribe-03-2026

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

From the file· summed bytes, KV per layer

Side by side

GLM-ASR-Nano-2512cohere-transcribe-03-2026
Parameters2.3B2.1B
Architectureglmasrcohere_asr
Layers28
Native context8,192
Mixture of expertsnono
Quantizations published511
Smallest quantization0.91 GiB1.41 GiB
Q4_K_M1.45 GiB
Licencemitapache-2.0

KV cache by context

the term that decides long-context viability
ContextGLM-ASR-Nano-2512cohere-transcribe-03-2026Ratio
4,0960.22 GiB
8,1920.44 GiB
16,3840.88 GiB
32,7681.75 GiB
65,5363.50 GiB
131,0727.00 GiB