How much VRAM does HyperCLOVAX-SEED-Text-Instruct-1.5B need?

Q4_K_M is exactly 1,133,974,368 bytes (1.06 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

naver-hyperclovax · text

HyperCLOVAX-SEED-Text-Instruct-1.5B

naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-1.5B

HyperCLOVAX-SEED-Text-Instruct-1.5B at Q4_K_M is exactly 1,133,974,368 bytes (1.06 GiB / 1.13 GB) — an effective 5.722 bits per weight, not the nominal 4.

From the file· summed from 1 file(s)

Parameters

1.6B

Architecture

llama

Context

—

native (config.json)

License

other

Shipped quantizations

● exact bytes, summed from published files

Quant	Size●	Exact bytes●	Effective bpw●	Tensors●	Publisher
Q4_K_M	1.06 GiB	1,133,974,368	5.722	219	rippertnt

Compare with

same modality, comparable size

vs Qwen3-4B vs Qwen3-8B vs Llama-3.2-1B-Instruct vs Qwen3-VL-8B-Instruct-abliterated-v1 vs Llama-3.1-8B-Instruct vs Qwen2.5-7B-Instruct All alternatives →Will it fit on my card? →

Why other calculators give a different number

A parameters × bits ÷ 8 estimate puts Q4_K_M at roughly 0.83 GiB. The real file is 1.06 GiB, because a quantization is a mixture and some tensors are always kept at higher precision.

Architecture

Architecture unavailable — this repository is gated and no ungated mirror was found. Exact file sizes above are still authoritative; only the KV math needs the config.

Questions people ask

How much VRAM does HyperCLOVAX-SEED-Text-Instruct-1.5B need?: Q4_K_M is exactly 1,133,974,368 bytes (1.06 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
Which quantization of HyperCLOVAX-SEED-Text-Instruct-1.5B should I use?: Q4_K_M is the usual default. Pick the largest quantization that fits your card at the context you actually need — the table above gives exact sizes for every one published.