Qwen3-Coder-Next

Qwen family · 80.0B params

1recorded run

174.3best tok/s

1verified

Evidence: 1 sourced run · 1 independent source · first recorded Aug 11, 2026. What these labels mean.

What the Qwen3-Coder-Next numbers mean

The fastest verified result on our board is 174.3 output tok/s on an RTX PRO 6000 Blackwell at FP8 with a 32768-token context. That is about 5.7 ms per generated token — 500 tokens takes roughly 2.9 seconds.

How much VRAM does Qwen3-Coder-Next need?

Qwen3-Coder-Next has 80.0B 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)	52.5 GB	64 GB
Q8_0 (8-bit)	98.5 GB	141 GB
FP16 (16-bit)	184.8 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)

RTX PRO 6000 Blackwell174.3

Models with a similar footprint

Model	Params	Q4_K_M weights
Llama-3.3-70B-Instruct	71B	39.9 GB
Llama-4-Scout-17B-16E-Instruct	109B	61.3 GB
Kimi-Linear-48B-A3B-Instruct	49B	27.6 GB
gpt-oss-120b	117B	65.8 GB
Laguna-S-2.1	118B	66.4 GB
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B	120B	67.5 GB

Ranked by distance from Qwen3-Coder-Next's parameter count. Full benchmark board.

All benchmarks Methodology

GPU	Model	Quant	Backend	Ctx	tok/s	prompt tok/s	VRAM GB	Source
RTX PRO 6000 Blackwell · 96 GB	Qwen3-Coder-Next	FP8	vllm 0.26.0	32768	174.3 ✓	—	—	src