I Tried PewDiePie’s Odysseus AI So You Don’t Have To (Its FREE)
Large local model needing about 77GB VRAM, downloaded via the Odysseus cookbook. Its SVG output was decent and clearly better than Gemma 3 12B, but well below GPT-5.5.
Q3
Qwen 3.5 122B
by Alibaba
Alibaba's Qwen 3.5 large open-weights language model (~122B parameters) from the Qwen family.
Updated EU status checked Last shown
Qwen 3.5 122B at a glance
- What is Qwen 3.5 122B?
- Qwen 3.5 122B is a model from Alibaba. Alibaba's Qwen 3.5 large open-weights language model (~122B parameters) from the Qwen family.
- Who makes Qwen 3.5 122B?
- Qwen 3.5 122B is made by Alibaba.
- Does Qwen 3.5 122B work in the EU?
- Available in the EU. Weights are downloadable from Hugging Face and were run locally by a creator; no EU exclusion was found in the provided material. The license was not verified. Last verified 14 Nov 2026.
- How much does Qwen 3.5 122B cost?
- Open source. Weights are downloadable for free for local use; hosted access via Qwen chat or API may have separate terms (not confirmed).
- Where was Qwen 3.5 122B shown?
- In 1 creator video by Matt Wolfe. Most recently by Matt Wolfe on 17 Jun 2026, at 10:41 in “I Tried PewDiePie’s Odysseus AI So You Don’t Have To (Its FREE)”.
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 3.5 122B is a large language model in Alibaba's Qwen family, published via the Qwen organisation on Hugging Face and GitHub. The provided material gives little detail about the model itself; the Qwen website describes the wider Qwen product as covering chat, image and video understanding, image generation, document processing, web search, tool use and artifacts.
A YouTube review (Matt Wolfe) describes running it locally, noting it needs about 77GB of VRAM. In that test, its SVG output was decent and clearly better than Gemma 3 12B, but well below GPT-5.5. This is a single informal impression, not a benchmark.
It can be used through Qwen's hosted chat and, as the weights are published, self-hosted on hardware with large memory. Architecture details, context length, exact license and release date were not confirmed in the provided pages.
Key features
- Roughly 122B-parameter model in the Qwen 3.5 series
- Reported to need about 77GB VRAM for local use
- Weights published through the Qwen Hugging Face organisation
- Usable via Qwen's hosted chat interface
- Decent SVG generation in one creator's test
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 3.8 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
Q3
Qwen 3.8 Max
Model · Alibaba
Alibaba's open-weights 2.4T-parameter MoE language model (95B active) from the Qwen3.8 family, with a hosted Max version.
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 Max
Model · Alibaba
Alibaba's Qwen flagship large language model, offered as a hosted proprietary model via Qwen Chat and Alibaba Cloud.
UnverifiedLanguage Models
Release date n/aAPI