Model comparison

Qwen3-1.7B-Distilled-30B-A3B-SFT vs Qwen3-VL-8B-Instruct-abliterated-v1

At Q4_K_M, Qwen3-1.7B-Distilled-30B-A3B-SFT is the smaller download — 1,282,439,072 bytes against 5,027,785,792.

From the file· summed bytes, KV per layer

Side by side

Qwen3-1.7B-Distilled-30B-A3B-SFTQwen3-VL-8B-Instruct-abliterated-v1
Parameters2.0B8.8B
Architectureqwen3qwen3vl
Layers28
Native context40,960
Mixture of expertsnono
Quantizations published448
Smallest quantization1.19 GiB1.97 GiB
Q4_K_M1.19 GiB4.68 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextQwen3-1.7B-Distilled-30B-A3B-SFTQwen3-VL-8B-Instruct-abliterated-v1Ratio
4,0960.44 GiB
8,1920.88 GiB
16,3841.75 GiB
32,7683.50 GiB
65,5367.00 GiB
131,07214.00 GiB