---
type: "Article"
title: "MiniCPM-V-4.7 35B-A3B INT4 with vLLM on 2× RTX 3090"
description: "MiniCPM-V-4.7 35B-A3B INT4 with vLLM on 2× RTX 3090: recipe by tonyd2wild with speed, condition and source for every number, weights and license."
resource: "https://www.contextstudios.ai/local-ai/tonyd2wild--minicpm-v-4.7-35b-a3b-int4-dspark-2x-rtx-3090"
language: "en"
generated:
  by: "process:contextstudios-md/1"
  at: "2026-11-11T03:20:46.758Z"
status: "stable"
---

# MiniCPM-V-4.7 35B-A3B INT4 with vLLM on 2× RTX 3090

MiniCPM-V-4.7 35B-A3B INT4 with vLLM on 2× RTX 3090: 199 tok/s according to github.com (dataset as of Nov 3, 2026).

- Creator: [tonyd2wild](https://www.contextstudios.ai/local-ai/creators/tonyd2wild.md)
- Engine: vLLM 0.31.1rc1.dev296 (nightly fe4df3d, torchcodec removed)
- Quantization: INT4 (compressed-tensors, OpenBMB) + DSpark draft BF16
- Model family: MiniCPM-V-4.7
- Hardware: rtx-3090 x2
- Context: 262144

## All numbers

- 199 tok/s (Everyday; Everyday, 1 request, prose prompt, with DSpark (per recipe)) — [source](https://github.com/tonyd2wild/MiniCPM-V-4.7-35B-A3B-2x-RTX-3090#draft-length-7-beats-the-model-cards-15)
- decode_tps: 198.7 (1 request) — [source](https://github.com/tonyd2wild/MiniCPM-V-4.7-35B-A3B-2x-RTX-3090#draft-length-7-beats-the-model-cards-15)
- decode_tps: 356 (1 request) — [source](https://github.com/tonyd2wild/MiniCPM-V-4.7-35B-A3B-2x-RTX-3090#draft-length-7-beats-the-model-cards-15)
- decode_tps: 654.9 (1 request) — [source](https://github.com/tonyd2wild/MiniCPM-V-4.7-35B-A3B-2x-RTX-3090#concurrency-sweep-with-the-draft-best-case-json)
- prefill_tps: 8304 (1 request) — [source](https://github.com/tonyd2wild/MiniCPM-V-4.7-35B-A3B-2x-RTX-3090/blob/main/results/speed/prefill_len_minicpm47-2x3090-tp2-nvl-dspark7.json)
- ttft_ms: 200 (1 request) — [source](https://github.com/tonyd2wild/MiniCPM-V-4.7-35B-A3B-2x-RTX-3090#concurrency-sweep-with-the-draft-best-case-json)

## Weights

- [openbmb/MiniCPM-V-4.7-35B-A3B-int4](https://huggingface.co/openbmb/MiniCPM-V-4.7-35B-A3B-int4) (main, apache-2.0)
- [openbmb/MiniCPM-V-4.7-35B-A3B](https://huggingface.co/openbmb/MiniCPM-V-4.7-35B-A3B) (base, apache-2.0)
- [openbmb/MiniCPM-V-4.7-35B-A3B-DSpark](https://huggingface.co/openbmb/MiniCPM-V-4.7-35B-A3B-DSpark) (draft, apache-2.0)

[https://github.com/tonyd2wild/MiniCPM-V-4.7-35B-A3B-2x-RTX-3090](https://github.com/tonyd2wild/MiniCPM-V-4.7-35B-A3B-2x-RTX-3090)

## Related

- [Local AI on your hardware.](https://www.contextstudios.ai/local-ai.md)