How much VRAM does LCO-Embedding-Omni-3B-2605 need?

Q4_K_M is exactly 2,104,931,744 bytes (1.96 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

LCO-Embedding · embedding

LCO-Embedding-Omni-3B-2605

LCO-Embedding/LCO-Embedding-Omni-3B-2605

LCO-Embedding-Omni-3B-2605 at Q4_K_M is exactly 2,104,931,744 bytes (1.96 GiB / 2.10 GB) — an effective 3.580 bits per weight, not the nominal 4.

From the file· summed from 1 file(s)From the file· KV per layer

Parameters

4.7B

Architecture

qwen2vl

36 layers

Context

32,768

native (config.json)

License

apache-2.0

Shipped quantizations

● exact bytes, summed from published files

Quant	Size●	Exact bytes●	Effective bpw●	Tensors●	Publisher
Q4_K_M	1.96 GiB	2,104,931,744	3.580	—	marksverdhei
Q5_K_M	2.27 GiB	2,438,739,360	4.148	—	marksverdhei
Q6_K	2.60 GiB	2,793,409,952	4.751	—	marksverdhei
Q8_0	3.37 GiB	3,616,087,456	6.151	—	marksverdhei

No KV cache

architectural, not a gap in our data

This architecture allocates no KV cache. Encoder and embedding models process their input in one pass rather than generating token by token, so there is nothing to carry forward between steps and memory does not grow with context. Its footprint is the weights plus a working buffer, and that is the whole story.

Compare with

same modality, comparable size

vs jina-embeddings-v5-text-small vs nomic-embed-text-v2-moe vs snowflake-arctic-embed-l-v2.0 vs Qwen3.5-9B-DFlash vs Qwen3-Embedding-0.6B vs Qwen3-Embedding-8B 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 2.46 GiB. The real file is 1.96 GiB, because a quantization is a mixture and some tensors are always kept at higher precision.

Architecture

from config.json

Layers

Attention heads

KV heads

Head dim

128

Hidden size

2048

Vocab

151,936

Sliding window

none

SWA period

—

MLA

Experts

—

Experts per token

—

use_sliding_window

false

Questions people ask

How much VRAM does LCO-Embedding-Omni-3B-2605 need?: Q4_K_M is exactly 2,104,931,744 bytes (1.96 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
Which quantization of LCO-Embedding-Omni-3B-2605 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.