Qwen 3.8 Flash-Next Base

Qwen family · 125.0B params

1recorded run

57.0best tok/s

1verified

Evidence: 1 sourced run · 1 independent source · first recorded Oct 12, 2026. What these labels mean.

What the Qwen 3.8 Flash-Next Base numbers mean

The fastest verified result on our board is 57.0 output tok/s on an Radeon AI Pro R9700 at IQ3_S with a 128000-token context. That is about 17.5 ms per generated token — 500 tokens takes roughly 8.8 seconds. Prompt processing on the same record runs at 119.4 tok/s, so a 2,000-token prompt is read in about 16.8 seconds.

How much VRAM does Qwen 3.8 Flash-Next Base need?

Qwen 3.8 Flash-Next Base has 125.0B 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)	81.7 GB	141 GB
Q8_0 (8-bit)	153.5 GB	192 GB
FP16 (16-bit)	288.3 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)

Radeon AI Pro R970057.0

Models with a similar footprint

Model	Params	Q4_K_M weights
Qwen 3.8 Flash	125B	70.3 GB
Ling-3.0-flash	127B	71.4 GB
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B	120B	67.5 GB
Laguna-S-2.1	118B	66.4 GB
gpt-oss-120b	117B	65.8 GB
Llama-4-Scout-17B-16E-Instruct	109B	61.3 GB

Ranked by distance from Qwen 3.8 Flash-Next Base's parameter count. Full benchmark board.

All benchmarks Methodology

GPU	Model	Quant	Backend	Ctx	tok/s	prompt tok/s	VRAM GB	Source
Radeon AI Pro R9700 · 32 GB	Qwen 3.8 Flash-Next Base	IQ3_S	xestrata xe0.1.42	128000	57.0 ✓	119.4	—	src