HyperCLOVAX-SEED-Text-Instruct-1.5B · rippertnt

HyperCLOVAX-SEED-Text-Instruct-1.5B Q4_K_M

This file is exactly 1,133,974,368 bytes — 1.06 GiB / 1.13 GB at an effective 5.722 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), summedFrom the file· 219 tensors parsed

Get it

1.06 GiB · 1 file
llama.cpp
llama-cli -hf rippertnt/HyperCLOVAX-SEED-Text-Instruct-1.5B-Q4_K_M-GGUF:Q4_K_M

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

Hugging Face CLI
hf download rippertnt/HyperCLOVAX-SEED-Text-Instruct-1.5B-Q4_K_M-GGUF hyperclovax-seed-text-instruct-1.5b-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.

Repository →
Size
1.06 GiB
1.13 GB
Effective bpw
5.722
from real bytes ÷ params
Tensors
219
Header
4.06 MB
GGUF metadata

What this quantization actually contains

per-tensor types, parsed from the GGUF header
Q4_K
145
F32
49
Q6_K
25

A quantization label names a mixture, not a uniform precision. Attention and output tensors are routinely kept at higher precision than the label implies, which is exactly why the effective bits-per-weight above exceeds the nominal rate.