Model comparison

LFM2.5-Audio-1.5B vs Qwen3-4B

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

From the file· summed bytes, KV per layer

Side by side

LFM2.5-Audio-1.5BQwen3-4B
Parameters1.5B4.0B
Architecturelfm2qwen3
Layers36
Native context40,960
Mixture of expertsnono
Quantizations published629
Smallest quantization0.80 GiB1.01 GiB
Q4_K_M2.33 GiB
Licenceother

KV cache by context

the term that decides long-context viability
ContextLFM2.5-Audio-1.5BQwen3-4BRatio
4,0960.56 GiB
8,1921.13 GiB
16,3842.25 GiB
32,7684.50 GiB
65,5369.00 GiB
131,07218.00 GiB