No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from AtomicChat/Qwen3.6-35B-A3B-UDT-MTP-GGUF
All models by AtomicChat →
Qwen3.6 35B A3B, self-quantized to GGUF by Atomic Chat. Built straight from Qwen's original weights with a per-tensor importance matrix, so this is not a repack of somebody else's files. Runs fully offline.
[!NOTE] These GGUFs are self-quantized from the original weights, not a repack. The importance matrix keeps low-bit quants closer to the full-precision model.
[!IMPORTANT] Always pass
--jinjaso the Qwen3.6 35B A3B chat template is applied. Without it the model can emit malformed turns.
[!NOTE] Qwen3.6 35B A3B is multimodal. This repo ships the
mmproj-BF16.ggufvision projector. With-hfit is pulled automatically; otherwise pass--mmproj. Usellama-mtmd-cliorllama-serverto feed images.
Run Qwen3.6 35B A3B locally with:
AtomicChat/Qwen3.6-35B-A3B-UDT-MTP-GGUF, pick a quant, hit Use this model.llama-server -hf AtomicChat/Qwen3.6-35B-A3B-UDT-MTP-GGUF:None --jinja -c 8192ollama run hf.co/AtomicChat/Qwen3.6-35B-A3B-UDT-MTP-GGUF:NoneQwen's recommended sampling configuration for Qwen/Qwen3.6-35B-A3B. Pass images through llama-mtmd-cli or llama-server with the projector.
Qwen/Qwen3.6-35B-A3B (original weights).--imatrix.Original model by Qwen, released under the Apache 2.0 license. Full terms: Apache 2.0. Quantized by Atomic Chat.
git clone https://github.com/ggml-org/llama.cppcmake llama.cpp -B llama.cpp/build -DBUILD_SHARED_LIBS=OFF -DGGML_CUDA=ONcmake --build llama.cpp/build --config Release -j --target llama-cli llama-server./llama.cpp/build/bin/llama-server \ -hf AtomicChat/Qwen3.6-35B-A3B-UDT-MTP-GGUF:None \ --jinja -ngl 99 -c 8192 -fa on