Ling-3.0-flash

Ling family · 127.0B params

2recorded runs

43.4best tok/s

1verified

Evidence: 1 sourced run · 1 awaiting review · 1 independent source · first recorded Aug 5, 2026 · last recorded Aug 8, 2026. What these labels mean.

What the Ling-3.0-flash numbers mean

The fastest verified result on our board is 39.3 output tok/s on an Radeon AI Pro R9700 x3 at Q4_0_ROCMFP4_STRIX_LEAN with a 4096-token context. That is about 25.4 ms per generated token — 500 tokens takes roughly 12.7 seconds. Prompt processing on the same record runs at 542.6 tok/s, so a 2,000-token prompt is read in about 3.7 seconds. Across the 2 records we hold for this model the range is 39.3–43.4 tok/s on 2 GPUs, because quantisation, context length and the engine build all move the number.

How much VRAM does Ling-3.0-flash need?

Ling-3.0-flash has 127.0B 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)	83.0 GB	141 GB
Q8_0 (8-bit)	156.0 GB	192 GB
FP16 (16-bit)	292.9 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)

Multi-GPU x343.4
Radeon AI Pro R9700 x339.3

Models with a similar footprint

Model	Params	Q4_K_M weights
Qwen 3.8 Flash	125B	70.3 GB
Qwen 3.8 Flash-Next Base	125B	70.3 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 Ling-3.0-flash'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 x3 · 32 GB	Ling-3.0-flash	Q4_0_ROCMFP4_STRIX_LEAN	llama.cpp ROCmFPX db6844d + BailingMoe3 port	4096	39.3 ✓	542.6	—	src
Multi-GPU x3 · 72 GB	Ling-3.0-flash	AD-IQ4_XXS	llama.cpp b10269-1.5.1 (build 10696, commit cd…	262144	43.4 …	—	68.4	src