Is Huihui-GLM-4.5-Air-abliterated-lossytensors or DeepSeek-V4-Flash smaller?

Both publish quantizations; compare the table for the exact sizes.

Which uses less memory at long context?

DeepSeek-V4-Flash — its KV cache at 32K context is 91.3x smaller, because of how its attention layers cache.

Model comparison

Huihui-GLM-4.5-Air-abliterated-lossytensors vs DeepSeek-V4-Flash

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: DeepSeek-V4-Flash's KV cache at 32K is 91.3× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Huihui-GLM-4.5-Air-abliterated-lossytensors	DeepSeek-V4-Flash
Parameters	110B	291B
Architecture	glm4moe	deepseek4
Layers	46	43
Native context	131,072	1,048,576
Mixture of experts	yes, 128 experts	yes, 256 experts
Quantizations published	2	12
Smallest quantization	41.88 GiB	76.87 GiB
Q4_K_M	—	—
Licence	mit	mit

KV cache by context

the term that decides long-context viability

Context	Huihui-GLM-4.5-Air-abliterated-lossytensors	DeepSeek-V4-Flash	Ratio
4,096	0.72 GiB	0.06 GiB	11.41×
8,192	1.44 GiB	0.06 GiB	22.82×
16,384	2.88 GiB	0.06 GiB	45.64×
32,768	5.75 GiB	0.06 GiB	91.29×
65,536	11.50 GiB	0.06 GiB	182.57×
131,072	23.00 GiB	0.06 GiB	365.15×