Story
RTX 5080 and RTX 3090 Setup: 80 Tok/s on Qwen 3.6 27B Q8
1 report
1 website
1 discussion
Latest report
Overview
An RTX 5080 and RTX 3090 setup achieves over 80 tokens per second on the Qwen 3.6 27B Q8 model. The RTX 3090, with 24GB of memory, significantly enhances performance, allowing for initial speeds of 30 tokens per second, increasing to 50-60 tokens per second with MTP.
Summary from imil.net.
Reports
One report so far. Additional coverage will appear here when it is linked to this story.
Community reactions
Each reaction summarizes sampled comments from the linked discussion.
Hacker News · imil.net
Hacker News discussion ↗
Historical count: 5 · 5 saved in sample · Historical sample
Analysis ready
Read this discussion’s reaction
Based on 5 sampled comments from this thread. Analyzed 2026-06-13.
- Praise: The RTX 5080 and 3090 combination achieving 80 tokens per second demonstrates impressive performance, showcasing the potential for high-throughput local inference.
- Praise: Users are finding more applications for Qwen 3.6 27B, indicating its versatility in various use cases, especially when answers are already present in the context.
- Praise: Local models like Qwen 3.6 can provide a straightforward failure mode, making it easier for users to identify issues compared to more complex models like Claude.
- Concern: The high cost of hardware and electricity makes local inference setups non-competitive with cloud options, limiting accessibility for many users.
- Concern: Concerns about the instability of software repositories, such as llamacpp, hinder the effective utilization of powerful hardware setups.
- Concern: Users express frustration over the lack of clarity regarding model versions and performance consistency when using hosted models like Claude.