unsloth/Qwen3-235B-A22B-Thinking-2507-GGUF · download link creates Q5_K_M instead of UD-Q5_K

Did you specifically use "Q5_K_XL" for the regex pattern when downloading?

Using the below works fine:

./llama.cpp/llama-cli \
    -hf unsloth/Qwen3-235B-A22B-Thinking-2507-GGUF:Q5_K_XL \
    --threads -1 \
    --ctx-size 16384 \
    --n-gpu-layers 99 \
    -ot ".ffn_.*_exps.=CPU" \
    --temp 0.6 \
    --min-p 0.0 \
    --top-p 0.95 \
    --top-k 20 \
    --presence-penalty 1.5

or:

# !pip install huggingface_hub hf_transfer
import os
os.environ["HF_HUB_ENABLE_HF_TRANSFER"] = "0" # Can sometimes rate limit, so set to 0 to disable
from huggingface_hub import snapshot_download
snapshot_download(
    repo_id = "unsloth/Qwen3-235B-A22B-Thinking-2507-GGUF",
    local_dir = "unsloth/Qwen3-235B-A22B-Thinking-2507-GGUF",
    allow_patterns = ["*UD-Q5_K_XL*"],
)

unsloth
/

Qwen3-235B-A22B-Thinking-2507-GGUF

download link creates Q5_K_M instead of UD-Q5_K_XL named files