rtx4070-super

Here are 3 public repositories matching this topic...

Run Qwen3.6-35B-A3B full native 258K context on 12GB VRAM (llama.cpp): ncmoe cliff rule, q4_0 KV prefill fix, 4 tuned profiles with scripts

windows moe quantization llama-cpp local-llm llm-inference qwen gguf qwen36 12gb-vram rtx4070-super

Run Qwen3.6-35B LLM + ComfyUI SDXL/Pony image gen simultaneously on 12GB VRAM — measured config (36-37 tok/s during render), scripts included

windows image-generation llama-cpp comfyui local-llm sd-xl qwen 12gb-vram rtx4070-super pony-v6

Run full 258K native context of Qwen3.6-35B-A3B MoE on 12GB VRAM with llama.cpp; benchmarked profiles, scripts, and tuning guide included.

windows moe quantization llama-cpp local-llm llm-inference qwen gguf qwen36 12gb-vram rtx4070-super

To associate your repository with the rtx4070-super topic, visit your repo's landing page and select "manage topics."