Comment Comment by Maxious ICYMI unsloth has had some major breakthroughs today with the Qwen3.5 local models https://unsloth.ai/docs/models/qwen3.5/gguf-benchmarksWith the Qwen3.5 35B A3B at Q4 I've got 200k context running at 62.98 tokens per second on a local RTX5080 16GB. parent Maxious 8 months ago
With the Qwen3.5 35B A3B at Q4 I've got 200k context running at 62.98 tokens per second on a local RTX5080 16GB.