MA
Who is local AI really for?Matthew Berman23 Oct 2026
Coding-specialist open model running at 50-130 tokens/s on an RTX 6000 Ada and 95-245 tokens/s on an RTX Pro 6000 Blackwell, single-threaded.
Alibaba's Qwen coding-specialist language model, available as open weights for local and hosted use.
Updated EU status checked Last shown
Qwen Coder Next at a glance
- What is Qwen Coder Next?
- Qwen Coder Next is a model from Alibaba. Alibaba's Qwen coding-specialist language model, available as open weights for local and hosted use.
- Who makes Qwen Coder Next?
- Qwen Coder Next is made by Alibaba.
- Does Qwen Coder Next work in the EU?
- Available in the EU. Reported as an open model that can be run locally, so it is generally usable in the EU; no explicit EU exclusion was found, but the license was not confirmed. Last verified 14 Nov 2026.
- How much does Qwen Coder Next cost?
- Open source. Described by a creator as an open model that can be run locally; hosted API pricing not confirmed.
- Where was Qwen Coder Next shown?
- In 1 creator video by Matthew Berman. Most recently by Matthew Berman on 23 Oct 2026, at 17:20 in “Who is local AI really for?”.
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
About
Qwen Coder Next is a coding-focused language model from Alibaba's Qwen team. It is aimed at code generation, completion and agent-style programming workflows. The provided material contains little detail beyond a creator mention, so specifics such as parameter count, context length and benchmark results are not confirmed here.
A YouTube creator (Matthew Berman) described it as an open coding-specialist model that can be run locally. He reported roughly 50-130 tokens/s on an RTX 6000 Ada and 95-245 tokens/s on an RTX Pro 6000 Blackwell in single-threaded use.
The Qwen website offers a chat interface and related features, while open-weight Qwen models are generally distributed through Hugging Face and similar channels. Exact license and download locations for this model were not confirmed from the provided pages.
Key features
- Coding-specialist model from the Qwen family
- Reported to run locally on workstation GPUs
- Reported 50-130 tokens/s on RTX 6000 Ada (single-threaded)
- Reported 95-245 tokens/s on RTX Pro 6000 Blackwell
1 moment
As seen on YouTube
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Keep exploring
Similar AI tools
Closest neighbours by meaning, not just by category.
Q3
Qwen 3.5 122B
Model · Alibaba
Alibaba's Qwen 3.5 large open-weights language model (~122B parameters) from the Qwen family.
Available in EULanguage Models
Release date n/aOpen source
Q3
Qwen 3.8 27B
Model · Alibaba
Compact 27B-parameter model from Alibaba's Qwen family, runnable locally on a single high-end consumer GPU.
Available in EULanguage Models
Release date n/aOpen source
Q3
Qwen 3.5 0.8B
Model · Alibaba
Small 0.8B-parameter open-weights language model in Alibaba's Qwen 3.5 family, aimed at lightweight and on-device use.
Available in EULanguage Models
Release date n/aOpen source
Q2
Qwen 2.5 0.5B
Model · Alibaba
Small 0.5B-parameter open-weights base language model from Alibaba's Qwen2.5 series, Apache 2.0 licensed.
Available in EULanguage Models
15 Sept 2024Open source
Q3
Qwen 3.8 Flash Next
Model · Alibaba
Alibaba's Qwen3.8 Flash Next: a 125B-parameter MoE language model with about 6B active parameters, previewing Qwen 4 design.
Available in EULanguage Models
Release date n/aOpen source
Q3
Qwen 3.7 Plus
Model · Alibaba
Alibaba's proprietary multimodal agentic model in the Qwen 3.7 series, aimed at long-horizon coding and tool-use tasks.
UnverifiedLanguage Models
Release date n/aAPI