Qwen3-1.7B

Qwen family · 2.0B params

1recorded run

198.1best tok/s

1verified

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

What the Qwen3-1.7B numbers mean

The fastest verified result on our board is 198.1 output tok/s on an RTX 3060 x2 at Q4_K_M with a 512-token context. That is about 5.0 ms per generated token — 500 tokens takes roughly 2.5 seconds. Prompt processing on the same record runs at 7121.2 tok/s, so a 2,000-token prompt is read in about 0.3 seconds. Peak VRAM was measured at 6.7 GB.

How much VRAM does Qwen3-1.7B need?

Qwen3-1.7B has 2.0B 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)	2.1 GB	8 GB
Q8_0 (8-bit)	3.2 GB	8 GB
FP16 (16-bit)	5.4 GB	8 GB

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 3060 x2198.1

Models with a similar footprint

Model	Params	Q4_K_M weights
Spark-X2.5-1.7B	2B	1.1 GB
gemma-3-1b-it	1B	0.6 GB
LFM2.5-1.2B-Instruct	1B	0.6 GB
LFM2.5-2.6B	3B	1.7 GB
Llama-3.2-1B-Instruct	1B	0.6 GB
Llama-3.2-3B-Instruct	3B	1.7 GB

Ranked by distance from Qwen3-1.7B's parameter count. Full benchmark board.

All benchmarks Methodology

GPU	Model	Quant	Backend	Ctx	tok/s	prompt tok/s	VRAM GB	Source
RTX 3060 x2 · 12 GB	Qwen3-1.7B	Q4_K_M	llama.cpp 13f2b28	512	198.1 ✓	7121.2	6.7	src