---
title: "DeepSeek-V3.2 on GB300: Performance Breakthrough"
url: https://daily.dev/posts/deepseek-v3-2-on-gb300-performance-breakthrough-3ccxkuvow
source_url: https://blog.vllm.ai/2026/02/13/gb300-deepseek.html
type: article
source: "vLLM"
published: 2026-02-13T12:25:14.675Z
updated: 2026-02-13T12:25:38.209Z
tags: ["performance", "llm", "nvidia", "deepseek", "vllm"]
reading_time: 11
upvotes: 1
comments: 0
language: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# DeepSeek-V3.2 on GB300: Performance Breakthrough

**[vLLM](https://daily.dev/sources/vllm)** · 11 min read · 1 upvotes · 0 comments

## Summary

DeepSeek-V3.2 and DeepSeek-R1 achieve significant performance gains on NVIDIA's GB300 (Blackwell Ultra) GPUs using FP4 quantization. DeepSeek-V3.2 reaches 7360 tokens/GPU/second in prefill-only scenarios with TP2 parallelization, while DeepSeek-R1 achieves 22476 TGS. Compared to Hopper H200, Blackwell shows 8x improvement in prefill and 10-20x in mixed-context scenarios. The article provides detailed benchmarking across different parallelization strategies (TP2 vs EP2), quantization formats (FP4 vs FP8), and deployment patterns including disaggregated prefill/decode architectures. DeepSeek-V3.2's Sparse MLA introduces overhead that limits prefill performance compared to R1, indicating room for optimization.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://blog.vllm.ai/2026/02/13/gb300-deepseek.html>

## Similar posts on daily.dev

- [Serving DeepSeek-V4 on GB300 with SGLang: 5x Higher Throughput at the Same Interactivity Since Day-0 – PyTorch](https://daily.dev/posts/serving-deepseek-v4-on-gb300-with-sglang-5x-higher-throughput-at-the-same-interactivity-since-day-0-mmxalpv2n) · PyTorch · 1 upvotes · 0 comments
- [Driving vLLM WideEP and Large-Scale Serving Toward Maturity on Blackwell \(Part I\)](https://daily.dev/posts/driving-vllm-wideep-and-large-scale-serving-toward-maturity-on-blackwell-part-i--36r4rera9) · vLLM · 1 upvotes · 0 comments

---

Tags: [#performance](https://daily.dev/tags/performance), [#llm](https://daily.dev/tags/llm), [#nvidia](https://daily.dev/tags/nvidia), [#deepseek](https://daily.dev/tags/deepseek), [#vllm](https://daily.dev/tags/vllm)

[View this post on daily.dev](https://daily.dev/posts/deepseek-v3-2-on-gb300-performance-breakthrough-3ccxkuvow)