Qwen3.5 27B Claude-4.6-Opus-Reasoning-Distilled-i1
on RTX 2070 8GB · Ollama · 8,192 ctx
Summary
User reports about 16 tok/s running a 27B Qwen3.5 reasoning-distilled model at IQ1_S on an RTX 2070 8GB.
Setup is Ollama with Open WebUI, an 8192-token context window, and an Intel Core i5-13600 CPU.
The user notes the model can solve river puzzles but fails to count the vowels in "BANANA", and describes the setup as a desperate measure for an 8GB GPU.