Qwen3-4B-Instruct · llmware
Qwen3-4B-Instruct Q4_K_M
This file is exactly 2,497,280,256 bytes — 2.33 GiB / 2.50 GB at an effective 4.967 bits per weight. The nominal rate for Q4_K_M is lower; mixed-precision tensors make the real figure higher, always.
From the file· 1 file(s), summed
Get it
2.33 GiB · 1 file
llama.cpp
llama-cli -hf llmware/qwen3-4b-instruct-gguf:Q4_K_M
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download llmware/qwen3-4b-instruct-gguf Qwen3-4B-Q4_K_M.gguf
Direct download
Straight from the Hugging Face CDN — we host nothing and earn nothing from this. Verify what you received against the exact byte count above; a size mismatch is the usual cause of a file that will not load.
Size
2.33 GiB
2.50 GB
Effective bpw
4.967
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata