MARTHA-2B-Qwen3.5-Omni · mradermacher

MARTHA-2B-Qwen3.5-Omni I1-Q3_K_S

This file is exactly 1,020,174,144 bytes — 0.95 GiB / 1.02 GB at an effective 4.337 bits per weight. The nominal rate for I1-Q3_K_S is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

0.95 GiB · 1 file
llama.cpp
llama-cli -hf mradermacher/MARTHA-2B-Qwen3.5-Omni-i1-GGUF:I1-Q3_K_S

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

Hugging Face CLI
hf download mradermacher/MARTHA-2B-Qwen3.5-Omni-i1-GGUF MARTHA-2B-Qwen3.5-Omni.i1-Q3_K_S.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
0.95 GiB
1.02 GB
Effective bpw
4.337
from real bytes ÷ params
Tensors
Header
GGUF metadata
MARTHA-2B-Qwen3.5-Omni I1-Q3_K_S — exact size and VRAM — ossmodeldb