MiniCPM-V 4.7-35B-A3B

MiniCPM-V family · 35.0B params

1recorded run

172.2best tok/s

1verified

Evidence: 1 sourced run · 1 independent source · first recorded Oct 13, 2026. What these labels mean.

What the MiniCPM-V 4.7-35B-A3B numbers mean

The fastest verified result on our board is 172.2 output tok/s on an RTX 3090 x2 at int4 with a 262144-token context. That is about 5.8 ms per generated token — 500 tokens takes roughly 2.9 seconds.

How much VRAM does MiniCPM-V 4.7-35B-A3B need?

MiniCPM-V 4.7-35B-A3B has 35.0B 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)	23.4 GB	32 GB
Q8_0 (8-bit)	43.6 GB	64 GB
FP16 (16-bit)	81.3 GB	96 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 3090 x2172.2

Models with a similar footprint

Model	Params	Q4_K_M weights
Apodex-1.1-mini	35B	19.7 GB
badtheorylabs_BTL-4	35B	19.7 GB
BTL-4-Compact	35B	19.7 GB
KAT-Coder-V2.5-Dev-AWQ-W4A16-ASYM	35B	19.7 GB
Kwaipilot_KAT-Coder-V2.5-Dev	35B	19.7 GB
Nex-N2-mini-B70-Turbo	35B	19.7 GB

Ranked by distance from MiniCPM-V 4.7-35B-A3B's parameter count. Full benchmark board.

All benchmarks Methodology

GPU	Model	Quant	Backend	Ctx	tok/s	prompt tok/s	VRAM GB	Source
RTX 3090 x2 · 24 GB	MiniCPM-V 4.7-35B-A3B	int4	vllm 0.31.1rc1.dev296 (nightly fe4df3d)	262144	172.2 ✓	—	—	src