CYBER-FROST-3.8

Qwen family · 180.0B params

1recorded run

60.7best tok/s

1verified

Evidence: 1 sourced run · 1 independent source · first recorded Oct 8, 2026. What these labels mean.

What the CYBER-FROST-3.8 numbers mean

The fastest verified result on our board is 60.7 output tok/s on an DGX Spark at EXL3 with a 400-token context. That is about 16.5 ms per generated token — 500 tokens takes roughly 8.2 seconds.

How much VRAM does CYBER-FROST-3.8 need?

CYBER-FROST-3.8 has 180.0B parameters. These estimates use the same formula as the VRAM calculator: weights, plus about 15% for a moderate-context KV cache and runtime overhead, plus a small engine floor.

Quantisation	Estimated VRAM	Smallest card that fits
Q4_K_M (4-bit)	117.2 GB	141 GB
Q8_0 (8-bit)	220.7 GB	multi-GPU or CPU offload
FP16 (16-bit)	414.8 GB	multi-GPU or CPU offload

Long contexts and large batches raise the real number — read the smallest card as "possible with a reduced context". Measured throughput is on the benchmark board.

Fastest GPUs for this model (best tok/s)

DGX Spark60.7

Models with a similar footprint

Model	Params	Q4_K_M weights
Qwen3.8-Flash-Next	180B	101.2 GB
Qwen3.8-Flash-Next-hibrid48	180B	101.2 GB
Qwen3.8-Flash-Next-REAP-256-duo	180B	101.2 GB
DeepSeek-V4-Flash-180B	158B	88.9 GB
MiniMax-M2.7	229B	128.8 GB
Ling-3.0-flash	127B	71.4 GB

Ranked by distance from CYBER-FROST-3.8's parameter count. Full benchmark board.

All benchmarks Methodology

GPU	Model	Quant	Backend	Ctx	tok/s	prompt tok/s	VRAM GB	Source
DGX Spark · 128 GB	CYBER-FROST-3.8	EXL3	exllamav2 047ce72	400	60.7 ✓	—	—	src