MiniCPM5-1B

Llama family · 1.0B params

2recorded runs

158.1best tok/s

1verified

Evidence: 1 sourced run · 1 awaiting review · 1 independent source · first recorded May 28, 2026 · last recorded Jul 8, 2026. What these labels mean.

What the MiniCPM5-1B numbers mean

The fastest verified result on our board is 125.9 output tok/s on an RTX 3060 x2 at Q4_K_M with a 128000-token context. That is about 7.9 ms per generated token — 500 tokens takes roughly 4.0 seconds. Prompt processing on the same record runs at 14828.4 tok/s, so a 2,000-token prompt is read in about 0.1 seconds. Peak VRAM was measured at 4.3 GB. Across the 2 records we hold for this model the range is 125.9–158.1 tok/s on 2 GPUs, because quantisation, context length and the engine build all move the number.

How much VRAM does MiniCPM5-1B need?

MiniCPM5-1B has 1.0B 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)	1.4 GB	8 GB
Q8_0 (8-bit)	2.0 GB	8 GB
FP16 (16-bit)	3.1 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)

RX 570 4GB x2158.1
RTX 3060 x2125.9

Models with a similar footprint

Model	Params	Q4_K_M weights
gemma-3-1b-it	1B	0.6 GB
LFM2.5-1.2B-Instruct	1B	0.6 GB
Llama-3.2-1B-Instruct	1B	0.6 GB
Qwen3-0.6B	1B	0.6 GB
Qwen3.5-0.8B	800M	0.5 GB
Qwen3.5-0.8B-MTP	800M	0.5 GB

Ranked by distance from MiniCPM5-1B'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	MiniCPM5-1B	Q4_K_M	llama.cpp 2cbfdc6	128000	125.9 ✓	14828.4	4.3	src
RX 570 4GB x2 · 4 GB	MiniCPM5-1B	Q4_K_M	llama.cpp —	2048	158.1 …	1144.5	—	src