Check my GPU

LLMs ·

LFM2 700M

Parameters
0.7B
Architecture
Dense
Max context
125K tokens
License
lfm1.0
Released
2025-07

How to run it

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

huggingface.co/LiquidAI/LFM2-700M-GGUF (opens in a new tab)

ollama run hf.co/LiquidAI/LFM2-700M-GGUF

Original weights · Hugging Face

Full-precision files from Liquid AI, for fine-tuning, vLLM, Transformers.

huggingface.co/LiquidAI/LFM2-700M (opens in a new tab)

No sign-in needed.

Links checked 5 days ago against Hugging Face, Ollama and GitHub.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps.

KV cache: hybrid convolution + attention: only the attention layers keep a KV cache.

Quantization Quality Weights Total at 8K context Total at 32K context Download
Q2_K Low 0.3 GB 1.0 GB 1.3 GB GGUF files (opens in a new tab)
Q3_K_M Low 0.4 GB 1.1 GB 1.4 GB GGUF files (opens in a new tab)
Q4_K_M Good 0.5 GB 1.2 GB 1.5 GB GGUF (opens in a new tab)
Q5_K_M High 0.5 GB 1.2 GB 1.5 GB GGUF (opens in a new tab)
Q6_K High 0.6 GB 1.3 GB 1.6 GB GGUF (opens in a new tab)
Q8_0 Very high 0.8 GB 1.5 GB 1.8 GB GGUF (opens in a new tab)
F16 Full 1.5 GB 2.2 GB 2.5 GB GGUF (opens in a new tab) Original weights (opens in a new tab)

Best hardware for LFM2 700M

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc A380 (launch price $139) at F16.

Grade · points Hardware Quant Memory Speed Fit
55 ptsUsable (C) · 55 of 100 points: Model quality 8.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.4/15 NVIDIA GeForce RTX 4060 F16 2.6 GB / 8.0 GB 106 tok/s Runs well
54 ptsUsable (C) · 54 of 100 points: Model quality 8.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.5/15 Apple M4 (16 GB) F16 3.0 GB / 10.7 GB 40.2 tok/s Runs well
53 ptsUsable (C) · 53 of 100 points: Model quality 8.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.3/15 Intel Arc B580 F16 2.8 GB / 12.0 GB 136 tok/s Runs well
53 ptsUsable (C) · 53 of 100 points: Model quality 8.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.3/15 NVIDIA GeForce RTX 3060 12GB F16 2.8 GB / 12.0 GB 140 tok/s Runs well
53 ptsUsable (C) · 53 of 100 points: Model quality 8.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.3/15 NVIDIA GeForce RTX 4070 SUPER F16 2.8 GB / 12.0 GB 196 tok/s Runs well
53 ptsUsable (C) · 53 of 100 points: Model quality 8.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.0/15 Apple M1 (16 GB) Q8_0 2.3 GB / 10.7 GB 49.6 tok/s Runs well
53 ptsUsable (C) · 53 of 100 points: Model quality 8.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.0/15 Apple M4 (24 GB) F16 3.5 GB / 16.1 GB 40.2 tok/s Runs well
53 ptsUsable (C) · 53 of 100 points: Model quality 8.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.0/15 Apple M4 Pro (24 GB) F16 3.5 GB / 16.1 GB 91.5 tok/s Runs well
52 ptsUsable (C) · 52 of 100 points: Model quality 8.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.3/15 AMD Radeon RX 9070 XT F16 3.0 GB / 16.0 GB 214 tok/s Runs well
52 ptsUsable (C) · 52 of 100 points: Model quality 8.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.3/15 NVIDIA GeForce RTX 4060 Ti 16GB F16 3.0 GB / 16.0 GB 112 tok/s Runs well

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.