Qwen3.5-9B-MedHELM-Reasoning-v1 I1-Q6_K

This file is exactly 7,558,902,304 bytes — 7.04 GiB / 7.56 GB at an effective 6.575 bits per weight. The nominal rate for I1-Q6_K is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

7.04 GiB · 1 file
llama.cpp
llama-cli -hf mradermacher/Qwen3.5-9B-MedHELM-Reasoning-v1-i1-GGUF:I1-Q6_K

Downloads and runs in one step, resolving the quantization by name.

Hugging Face CLI
hf download mradermacher/Qwen3.5-9B-MedHELM-Reasoning-v1-i1-GGUF Qwen3.5-9B-MedHELM-Reasoning-v1.i1-Q6_K.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
7.04 GiB
7.56 GB
Effective bpw
6.575
from real bytes ÷ params
Tensors
Header
GGUF metadata
Qwen3.5-9B-MedHELM-Reasoning-v1 I1-Q6_K — exact size and VRAM — ossmodeldb