Qwen3.8 27b just exceeded my expectations on svg generation :D
Summary
A user tested the Qwen3.8 27B model on SVG generation with a complex prompt and found the results exceeded expectations, highlighting the model's capability in creative tasks.
Similar Articles
Qwen 3.6 35B A3B Q8_0 "Create an SVG of a Darth Vader." at various expert counts.
Evaluation of Qwen 3.6 35B A3B Q8_0 model's SVG generation capability by testing with varying expert counts on the prompt 'Create an SVG of a Darth Vader.'
Asked Qwen3.8-27B to draw a pelican, it proceeded to draw an entire animation in svg!
When asked to draw a pelican, the AI model Qwen3.8-27B unexpectedly created a full SVG animation, demonstrating its advanced generative abilities.
I just ran Qwen 3.8 27 in Q4 against GPT 5.6 Sol high - and it easily won against SOL - complex animated SVG tasks
A user tested Qwen 3.8 27B in Q4 quantization against GPT 5.6 SOL in complex animated SVG tasks and found that Qwen performed better with fewer errors, highlighting strengths in spatial reasoning and coding.
qwen3.8-27b holy mother of god
User expresses excitement about the impressive performance of Qwen3 8B and 27B models, sharing an image of results.
Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model
Qwen releases Qwen3.6-27B, a 27B dense model claiming flagship-level coding performance surpassing the larger Qwen3.5-397B-A17B MoE, with impressive SVG generation demos.