How much VRAM does SmolVLM-256M-Instruct need?

Q8_0 is exactly 175,054,528 bytes (0.16 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

How large is SmolVLM-256M-Instruct's KV cache?

0.70 GiB at 32K context with an f16 cache, computed per layer from the model's architecture. Quantizing the cache to q8_0 roughly halves it.

HuggingFaceTB · text

SmolVLM-256M-Instruct

HuggingFaceTB/SmolVLM-256M-Instruct

SmolVLM-256M-Instruct at Q8_0 is exactly 175,054,528 bytes (0.16 GiB / 0.18 GB) — an effective 5.460 bits per weight, not the nominal 8. Its KV cache at 32K is 0.70 GiB.

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

Parameters

256M

Architecture

llama

30 layers

Context

8,192

native (config.json)

License

apache-2.0

Shipped quantizations

● exact bytes, summed from published files

Quant	Size●	Exact bytes●	Effective bpw●	Tensors●	Publisher
Q8_0	0.16 GiB	175,054,528	5.460	—	ggml-org
F16	0.31 GiB	327,809,728	10.225	—	ggml-org

KV cache by context

computed per layer

Context	KV cache (f16)●	Flat formula	Overstated by	Full / windowed / recurrent
4,096	0.09 GiB	0.09 GiB	—	30 / 0 / 0
8,192	0.18 GiB	0.18 GiB	—	30 / 0 / 0
16,384	0.35 GiB	0.35 GiB	—	30 / 0 / 0
32,768	0.70 GiB	0.70 GiB	—	30 / 0 / 0
65,536	1.41 GiB	1.41 GiB	—	30 / 0 / 0
131,072	2.81 GiB	2.81 GiB	—	30 / 0 / 0

Compare with

same modality, comparable size

vs Llama-3.2-1B-Instruct vs ced-base vs embeddinggemma-300m vs Qwen3-0.6B vs Qwen2.5-0.5B-Instruct vs SmolLM2-135M-Instruct All alternatives →Will it fit on my card? →

Why other calculators give a different number

A parameters × bits ÷ 8 estimate puts Q8_0 at roughly 0.13 GiB. The real file is 0.16 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

Hidden size

576

Vocab

49,280

Sliding window

none

SWA period

—

MLA

Experts

—

Experts per token

—

use_sliding_window

—

Questions people ask

How much VRAM does SmolVLM-256M-Instruct need?: Q8_0 is exactly 175,054,528 bytes (0.16 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
How large is SmolVLM-256M-Instruct's KV cache?: 0.70 GiB at 32K context with an f16 cache, computed per layer. Quantizing the cache to q8_0 roughly halves it, which is often the difference between a context length fitting and not.
Which quantization of SmolVLM-256M-Instruct 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.