RunsOnMy ModelsGPUs & MacsBy VRAMBest GPUCan I run…?OllamaStart hereAPI pricesVRAM calculatorNew

Can I run LFM2 1.2B locally?

LFM2 1.2B by LiquidAI has 1.2B parameters. At 4-bit with an 8K context it needs about 1.5 GB of GPU memory. It fits on 65 of 65 GPUs and Macs we track. See all models that fit in 8 GB of VRAM.

1.5 GBQ4_K_M · 8K context
RTX 4060smallest consumer GPU that fits
M1 16GBsmallest Mac that fits
125Kmax context
GQAattention type

Memory needed by quant and context length

GB of GPU memory = weights + KV cache (FP16) + runtime overhead. Weights use real file sizes from LiquidAI/LFM2-1.2B-GGUF where available (marked •), otherwise parameter count × bits per weight. How we calculate.

QuantQuality4K ctx8K ctx32K ctx
2-bit (Q2_K)rough1.1 GB1.2 GB1.9 GB
3-bit (Q3_K_M)usable1.2 GB1.3 GB2.1 GB
4-bit (Q4_K_M) •good, most popular1.3 GB1.5 GB2.2 GB
5-bit (Q5_K_M) •very good1.4 GB1.6 GB2.3 GB
6-bit (Q6_K) •near lossless1.5 GB1.7 GB2.4 GB
8-bit (Q8_0) •effectively lossless1.8 GB1.9 GB2.7 GB
16-bit (F16/BF16) •original weights2.8 GB3.0 GB3.7 GB

Which GPUs and Macs run LFM2 1.2B?

Best quality quant that fits at 8K context. "Tight" = within 10% of usable memory. Speed is a ceiling from memory bandwidth (real speed is typically 50–80% of it).

HardwareMemoryFits?Best quantNeedsMax tok/s (est.)Details
RTX 3060 12GB12 GBFitsF163.0 GB154details
RTX 4060 Ti 16GB16 GBFitsF163.0 GB123details
RTX 309024 GBFitsF163.0 GB399details
RTX 409024 GBFitsF163.0 GB430details
RTX 509032 GBFitsF163.0 GB765details
RTX 5070 Ti16 GBFitsF163.0 GB382details
RX 7900 XTX24 GBFitsF163.0 GB410details
Mac M4 Pro 48GB48 GBFitsF163.0 GB117details
Mac M4 Max 128GB128 GBFitsF163.0 GB233details
Mac M3 Ultra 512GB512 GBFitsF163.0 GB350details
DGX Spark128 GBFitsF163.0 GB117details
RTX 407012 GBFitsF163.0 GB215details
RTX 5060 Ti 16GB16 GBFitsF163.0 GB191details
RTX 40608 GBFitsF163.0 GB116details
Arc B58012 GBFitsF163.0 GB195details
RTX 3060 Ti8 GBFitsF163.0 GB191details
RTX 30708 GBFitsF163.0 GB191details
RTX 3080 10GB10 GBFitsF163.0 GB324details
RTX 3080 12GB12 GBFitsF163.0 GB389details
RTX 3090 Ti24 GBFitsF163.0 GB430details
RTX 4060 Ti 8GB8 GBFitsF163.0 GB123details
RTX 4070 Super12 GBFitsF163.0 GB215details
RTX 4070 Ti12 GBFitsF163.0 GB215details
RTX 4070 Ti Super16 GBFitsF163.0 GB287details
RTX 408016 GBFitsF163.0 GB306details
RTX 4080 Super16 GBFitsF163.0 GB314details
RTX 50608 GBFitsF163.0 GB191details
RTX 507012 GBFitsF163.0 GB287details
RTX 508016 GBFitsF163.0 GB410details
2x RTX 30902×24 GBFitsF163.0 GB399details
2x RTX 40902×24 GBFitsF163.0 GB430details
2x RTX 50902×32 GBFitsF163.0 GB765details
RTX A600048 GBFitsF163.0 GB328details
RTX 6000 Ada48 GBFitsF163.0 GB410details
RTX PRO 6000 Blackwell96 GBFitsF163.0 GB765details
L40S48 GBFitsF163.0 GB369details
A100 40GB40 GBFitsF163.0 GB664details
A100 80GB80 GBFitsF163.0 GB870details
H100 PCIe80 GBFitsF163.0 GB853details
H100 SXM80 GBFitsF163.0 GB1430details
H200141 GBFitsF163.0 GB2048details
RX 76008 GBFitsF163.0 GB123details
RX 7700 XT12 GBFitsF163.0 GB184details
RX 7800 XT16 GBFitsF163.0 GB266details
RX 7900 GRE16 GBFitsF163.0 GB246details
RX 7900 XT20 GBFitsF163.0 GB341details
RX 907016 GBFitsF163.0 GB273details
RX 9070 XT16 GBFitsF163.0 GB273details
Ryzen AI Max+ 395 128GB128 GBFitsF163.0 GB109details
Arc A770 16GB16 GBFitsF163.0 GB239details
Mac M1 16GB16 GBFitsF163.0 GB29details
Mac M2 24GB24 GBFitsF163.0 GB43details
Mac M3 24GB24 GBFitsF163.0 GB43details
Mac M4 16GB16 GBFitsF163.0 GB51details
Mac M4 32GB32 GBFitsF163.0 GB51details
Mac M1 Pro 32GB32 GBFitsF163.0 GB85details
Mac M3 Pro 36GB36 GBFitsF163.0 GB64details
Mac M4 Pro 24GB24 GBFitsF163.0 GB117details
Mac M4 Pro 64GB64 GBFitsF163.0 GB117details
Mac M1 Max 64GB64 GBFitsF163.0 GB171details
Mac M2 Max 96GB96 GBFitsF163.0 GB171details
Mac M3 Max 128GB128 GBFitsF163.0 GB171details
Mac M4 Max 64GB64 GBFitsF163.0 GB233details
Mac M2 Ultra 192GB192 GBFitsF163.0 GB341details
Mac M3 Ultra 256GB256 GBFitsF163.0 GB350details

Questions

How much VRAM does LFM2 1.2B need?

About 1.5 GB at 4-bit (Q4_K_M) with an 8K context: 0.7 GB of weights (real GGUF file size), 0.3 GB of KV cache and 0.5 GB of runtime overhead. At 8-bit it needs about 1.9 GB.

What is the smallest GPU that runs LFM2 1.2B?

At Q4_K_M and 8K context, the smallest single consumer GPU in our table that fits it is the RTX 4060 (8 GB).

Can I run LFM2 1.2B on a Mac?

Yes. At Q4_K_M with 8K context it fits on a Mac M1 16GB or larger, using the default macOS GPU memory limit.

Similar models

Same family or a similar parameter count, with the VRAM each needs at Q4_K_M and 8K context.

LFM2.5 1.2B Instruct

1.2B · 1.3 GB at 4-bit

LFM3 1.7B

1.7B · 1.8 GB at 4-bit

LFM3 1.7B Base

1.7B · 1.8 GB at 4-bit

HunyuanOCR

1.1B · 2.0 GB at 4-bit

Llama 3.2 1B

1.2B · 1.6 GB at 4-bit

Llama 3.2 1B Instruct

1.2B · 1.6 GB at 4-bit

Embed this

LFM2 1.2B: runs on 8 GB+ VRAM Free badge and "Will it run on my GPU?" widget for model cards, READMEs and blogs. No cookies, no tracking. All options.

Copy a snippet

Markdown badge

[![LFM2 1.2B: runs on 8 GB+ VRAM (RunsOnMy)](https://runsonmy.com/badge/lfm2-1-2b.svg)](https://runsonmy.com/model/lfm2-1-2b/)

Widget (script)

<div class="runsonmy-widget" data-model="lfm2-1-2b"><a href="https://runsonmy.com/model/lfm2-1-2b/">Will LFM2 1.2B run on my GPU? Check on RunsOnMy</a></div>
<script async src="https://runsonmy.com/embed.js"></script>

Widget (iframe)

<iframe src="https://runsonmy.com/embed/m/lfm2-1-2b/" width="100%" height="220" style="max-width:440px;border:0" loading="lazy" title="Will LFM2 1.2B run on my GPU? (RunsOnMy)"></iframe>

Model facts

Hugging Face repoLiquidAI/LFM2-1.2B
Parameters1,170,340,608 (1.2B)
Layers / hidden size16 / 2048
AttentionGQA; 32 heads, 8 KV heads, head dim 64
KV cache per token (FP16)32.0 KiB
Max context128,000 tokens
Licenseother
Released on HFJul 10, 2025
Downloads (30d) / likes16,248 / 370

Sources: Hugging Face model API · config.json (LiquidAI/LFM2-1.2B) · GGUF files · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.