How much VRAM does LFM2.5-1.2B-Instruct-Uncensored need?

Q4_K_M is exactly 730,895,520 bytes (0.68 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

How large is LFM2.5-1.2B-Instruct-Uncensored's KV cache?

0.38 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.

zaakirio · text

LFM2.5-1.2B-Instruct-Uncensored

zaakirio/LFM2.5-1.2B-Instruct-Uncensored

LFM2.5-1.2B-Instruct-Uncensored at Q4_K_M is exactly 730,895,520 bytes (0.68 GiB / 0.73 GB) — an effective 4.996 bits per weight, not the nominal 4. Its KV cache at 32K is 0.38 GiB.

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

Parameters

1.2B

Architecture

lfm2

16 layers

Context

128,000

native (config.json)

License

other

Shipped quantizations

● exact bytes, summed from published files

Quant	Size●	Exact bytes●	Effective bpw●	Tensors●	Publisher
Q3_K_M	0.56 GiB	600,347,808	4.104	—	zaakirio
Q4_K_M	0.68 GiB	730,895,520	4.996	—	zaakirio
Q5_K_M	0.79 GiB	843,355,296	5.765	—	zaakirio
Q6_K	0.90 GiB	962,843,808	6.582	—	zaakirio
Q8_0	1.16 GiB	1,246,254,240	8.519	—	zaakirio

KV cache by context

computed per layer

Context	KV cache (f16)●	Flat formula	Overstated by	Full / windowed / recurrent
4,096	0.05 GiB	0.13 GiB	2.67×	6 / 0 / 10
8,192	0.09 GiB	0.25 GiB	2.67×	6 / 0 / 10
16,384	0.19 GiB	0.50 GiB	2.67×	6 / 0 / 10
32,768	0.38 GiB	1.00 GiB	2.67×	6 / 0 / 10
65,536	0.75 GiB	2.00 GiB	2.67×	6 / 0 / 10
131,072	1.50 GiB	4.00 GiB	2.67×	6 / 0 / 10

10 of 16 layers use linear attention, which keeps a fixed-size recurrent state instead of a per-token cache. Those layers do not grow with context at all — treating them as ordinary attention, as a flat formula does, overstates this model's cache by roughly 2.7× at long context.

Compare with

same modality, comparable size

vs Qwen3-4B vs HyperCLOVAX-SEED-Text-Instruct-1.5B vs Llama-3.2-1B-Instruct vs ced-base vs gemma-3-1b-it vs Qwen3-1.7B 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 0.61 GiB. The real file is 0.68 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

2048

Vocab

65,536

Sliding window

none

SWA period

—

MLA

Experts

—

Experts per token

—

use_sliding_window

—

Questions people ask

How much VRAM does LFM2.5-1.2B-Instruct-Uncensored need?: Q4_K_M is exactly 730,895,520 bytes (0.68 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
How large is LFM2.5-1.2B-Instruct-Uncensored's KV cache?: 0.38 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 LFM2.5-1.2B-Instruct-Uncensored 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.