---
type: "Article"
title: "MiniCPM-V-4.7 35B-A3B INT4 mit vLLM auf 2× RTX 3090"
description: "MiniCPM-V-4.7 35B-A3B INT4 mit vLLM auf 2× RTX 3090: Rezept von tonyd2wild mit Tempo, Bedingung und Quelle je Zahl, Gewichten und Lizenz."
resource: "https://www.contextstudios.ai/de/lokale-ki/tonyd2wild--minicpm-v-4.7-35b-a3b-int4-dspark-2x-rtx-3090"
language: "de"
generated:
  by: "process:contextstudios-md/1"
  at: "2026-11-10T13:49:34.556Z"
status: "stable"
---

# MiniCPM-V-4.7 35B-A3B INT4 mit vLLM auf 2× RTX 3090

MiniCPM-V-4.7 35B-A3B INT4 mit vLLM auf 2× RTX 3090: 199 tok/s laut github.com (Datensatz-Stand: 3. Nov. 2026).

- Kreator: [tonyd2wild](https://www.contextstudios.ai/de/lokale-ki/kreatoren/tonyd2wild.md)
- Engine: vLLM 0.31.1rc1.dev296 (nightly fe4df3d, torchcodec removed)
- Quantisierung: INT4 (compressed-tensors, OpenBMB) + DSpark draft BF16
- Modellfamilie: MiniCPM-V-4.7
- Hardware: rtx-3090 x2
- Kontext: 262144

## Alle Zahlen

- 199 tok/s (Alltag; Alltag, 1 Anfrage, Prosa-Prompt, mit DSpark (laut Rezept)) — [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 Anfrage) — [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 Anfrage) — [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 Anfrage) — [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 Anfrage) — [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 Anfrage) — [source](https://github.com/tonyd2wild/MiniCPM-V-4.7-35B-A3B-2x-RTX-3090#concurrency-sweep-with-the-draft-best-case-json)

## Gewichte

- [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

- [Lokale KI auf Ihrer Hardware.](https://www.contextstudios.ai/de/lokale-ki.md)