goodasdgood/Qwen3.6-35B-custom-mixed.gguf overview
https://github.com/ayttop/suc Qwen3.6 35B custom mixedgguf https://github.com/ayttop/suc Qwen3.6 35B custom mixedgguf/blob/main/Qwen3 6 35B custom mixedgguf%20…
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Browse files on Hugging Face | ||||
Model Details
| Model ID | goodasdgood/Qwen3.6-35B-custom-mixed.gguf |
|---|---|
| Author | goodasdgood |
| Pipeline | — |
| License | apache-2.0 |
| Base model | — |
| Last modified | 2026-09-22T01:46:49.000Z |
Model README
---
license: apache-2.0
---
https://github.com/ayttop/suc-Qwen3.6-35B-custom-mixedgguf
https://github.com/ayttop/suc-Qwen3.6-35B-custom-mixedgguf/blob/main/Qwen3_6_35B_custom_mixedgguf%20(1).ipynb
!curl -LsSf https://llama.app/install.sh | sh
unsloth/Qwen3.6-35B-A3B-MTP-GGUF
https://huggingface.co/unsloth/Qwen3.6-35B-A3B-MTP-GGUF/tree/main/BF16
!~/.llama-app/llama quantize \
--leave-output-tensor \
--token-embedding-type F16 \
--tensor-type "ffn_gate_inp=F16" \
--tensor-type "attn_v=F16" \
--tensor-type "attn_output=F16" \
--tensor-type "ffn_down=F16" \
/content/Qwen3.6-35B-A3B-BF16-00001-of-00002.gguf \
/content/Qwen3.6-35B-custom-mixed.gguf \
Q3_K_M \
$(nproc)
colab
v5e-1 TPU
ram 47gb
harh225gb
Run goodasdgood/Qwen3.6-35B-custom-mixed.gguf with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models