LFM2.5 Thinking 1.2B

Overview

Liquid AI's 1.2B reasoning variant with an explicit thinking mode, sub-1GB Q4 footprint, and CPU/iGPU-friendly inference. 32k context.

When to pick this model

• On-device reasoning on laptops and SBCs without a discrete GPU
• Latency-sensitive tasks that still benefit from chain-of-thought
• Edge agents where memory budget rules out larger models
• Privacy-first deployments that must stay fully local

VRAM requirements by quantization

Quantization	VRAM required
Q4_K_M (recommended)	0.7 GB
Q5_K_M	0.9 GB
Q8_0	1.3 GB
FP16 (no quantization)	2.4 GB

VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.

In practice, LFM2.5 Thinking 1.2B fits an 8 GB consumer card at Q4_K_M (0.7 GB). Stepping up to Q8_0 nearly doubles the footprint to 1.3 GB, and unquantized FP16 weights take 2.4 GB — plan your GPU around the Q4 or Q5 figure unless you specifically need the higher fidelity.

Without a GPU, LFM2.5 Thinking 1.2B needs roughly 1.6 GB of system RAM to run on CPU via llama.cpp or Ollama — workable for background jobs, but far slower than GPU inference. Throughput estimates from our compatibility engine: around 110 tokens/sec on entry-level GPUs, on the order of 170 tokens/sec on a mid-range card, and up to 220 tokens/sec on high-end hardware — assuming the chosen quantization fully fits in VRAM.

What hardware do you need

The table below matches LFM2.5 Thinking 1.2B to common GPU memory tiers, using the highest-fidelity quantization that fully fits each card class. Spilling layers to system RAM works but costs most of the speed, so size your card to the quantization you actually want to run.

GPU memory	Example cards	Best fit for LFM2.5 Thinking 1.2B
8 GB	RTX 5070 Laptop, RTX 5060, RTX 5060 Ti 8GB	FP16 (2.4 GB used)
12 GB	RTX 5070, RTX 5070 Ti Laptop, RTX 4080 Laptop	FP16 (2.4 GB used)
16 GB	RTX 5080, RTX 4080 Super, Radeon RX 9070 XT	FP16 (2.4 GB used)
24 GB	RTX 4090, Radeon RX 7900 XTX, RTX 5090 Laptop	FP16 (2.4 GB used)
32 GB	RTX 5090	FP16 (2.4 GB used)

Which GPU should you buy to run LFM2.5 Thinking 1.2B?

To run LFM2.5 Thinking 1.2B locally at Q4, you need ~0.7 GB of VRAM. The best value for this is a RTX 5060 (8 GB VRAM).

Strengths

• Negligible memory footprint — under 1GB at Q4
• Runs comfortably on CPU and integrated GPUs
• Explicit thinking mode for visible chain-of-thought
• Low-latency inference suitable for interactive use

Limitations

• 1.2B parameters cap absolute capability
• 32k context is short by 2026 standards
• LFM Open License rather than pure Apache

Typical workloads

In our catalog grid, LFM2.5 Thinking 1.2B is filed under Edge Reasoning, CPU / iGPU, Mobile and Lightweight Laptop — the use cases where its size/quality trade-off makes the most sense. Its tags translate to concrete workloads: multi-step reasoning and math-flavoured tasks.

The 32k-token context window covers long chats and mid-sized documents, though very large retrieval workloads will need chunking. It ships under the LFM Open License v1.0 license — commercial use is generally possible but read the specific terms before embedding it in a product.

Architecture & training

Architecture: Liquid Foundation Model · 1.2B parameters · 32k context · thinking mode

Training: Liquid AI's LFM2.5 family. Reasoning variant with explicit chain of thought.

Quick start

ollama run lfm2.5-thinking

Or use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.

Similar models worth comparing

Frequently asked questions

How much VRAM does LFM2.5 Thinking 1.2B need?

At the recommended Q4_K_M quantization, LFM2.5 Thinking 1.2B needs about 0.7 GB of VRAM. Q8_0 takes 1.3 GB, and unquantized FP16 weights take 2.4 GB.

Can LFM2.5 Thinking 1.2B run without a GPU?

Yes — with roughly 1.6 GB of system RAM it runs CPU-only through llama.cpp or Ollama. Expect a fraction of GPU speed, which is fine for background or batch jobs but slow for interactive chat.

What context window does LFM2.5 Thinking 1.2B support?

LFM2.5 Thinking 1.2B supports a 32k-token context window (32,768 tokens).

Can I use LFM2.5 Thinking 1.2B commercially?

LFM2.5 Thinking 1.2B ships under the LFM Open License v1.0 license. Commercial use is generally permitted subject to its terms — review the license text before shipping a product.

How fast is LFM2.5 Thinking 1.2B on consumer hardware?

Our compatibility engine estimates on the order of 170 tokens/sec on a mid-range GPU and up to 220 tokens/sec on high-end cards, assuming the quantization fully fits in VRAM.

Which quantization of LFM2.5 Thinking 1.2B should I download first?

Start with Q4_K_M (0.7 GB) — the standard size/quality sweet spot. Step up to Q5_K_M or Q8_0 only if you have VRAM headroom. It already fits an 8 GB card at FP16.