Run LiquidAI/LFM2.5-1.2B-Instruct-GGUF locally

License: other ⬇ 248,054 ❤ 189
Parameters1.17B
Context128,000

LiquidAI/LFM2.5-1.2B-Instruct-GGUF is a compact instruction-tuned chat model with 1.17 billion parameters, built on the lfm2 architecture. It is released under the other license and has been downloaded 248,054 times.

To run LiquidAI/LFM2.5-1.2B-Instruct-GGUF locally at a 4,096-token context, its quantized versions need between 1.95 GB (Q4_0, lowest quality) and 3.48 GB (BF16, highest quality) of memory, weights plus KV cache and a system margin included.

For most users the best balance is BF16, needing about 3.48 GB. That means LiquidAI/LFM2.5-1.2B-Instruct-GGUF fits entirely in the VRAM of a 6 GB GPU or larger, running fully on the GPU.

→ Guide: How much VRAM do you need?

All quantizations

Quant.Bits QualityWeights KVTotal Speed~Verdict
Q4_0 4.76 Good 0.65 GB 0.5 GB 1.95 GB 617.3 t/s Fits in VRAM
Q4_K_M 5.0 Good 0.68 GB 0.5 GB 1.98 GB 587.6 t/s Fits in VRAM
Q5_K_M 5.76 Very good 0.79 GB 0.5 GB 2.09 GB 509.3 t/s Fits in VRAM
Q6_K 6.58 Excellent 0.9 GB 0.5 GB 2.2 GB 446.1 t/s Fits in VRAM
Q8_0 8.52 Excellent 1.16 GB 0.5 GB 2.46 GB 344.6 t/s Fits in VRAM
BF16 16.02 Excellent 2.18 GB 0.5 GB 3.48 GB 183.3 t/s Fits in VRAM
F16 16.02 Excellent 2.18 GB 0.5 GB 3.48 GB 183.3 t/s Fits in VRAM

KV cache computed from the model's exact architecture. Speed is a rough estimate bounded by memory bandwidth.

Frequently asked questions

How much VRAM do you need to run LiquidAI/LFM2.5-1.2B-Instruct-GGUF?

You need about 3.48 GB of VRAM to run LiquidAI/LFM2.5-1.2B-Instruct-GGUF entirely on the GPU using the BF16 quantization (at a 4,096-token context). Smaller quantizations lower the requirement at the cost of quality.

Can I run LiquidAI/LFM2.5-1.2B-Instruct-GGUF on an 8 GB GPU?

Yes. With 8 GB of VRAM you can run LiquidAI/LFM2.5-1.2B-Instruct-GGUF fully on the GPU using BF16 (about 3.48 GB).

Can I run LiquidAI/LFM2.5-1.2B-Instruct-GGUF on a 16 GB GPU?

Yes. With 16 GB of VRAM you can run LiquidAI/LFM2.5-1.2B-Instruct-GGUF fully on the GPU using BF16 (about 3.48 GB).

Can I run LiquidAI/LFM2.5-1.2B-Instruct-GGUF on a 24 GB GPU?

Yes. With 24 GB of VRAM you can run LiquidAI/LFM2.5-1.2B-Instruct-GGUF fully on the GPU using BF16 (about 3.48 GB).

What is the best quantization for LiquidAI/LFM2.5-1.2B-Instruct-GGUF?

If memory allows, higher bits-per-weight means better quality. A common sweet spot is a Q4_K_M or Q5_K_M quantization, which keeps most of the quality while roughly halving the memory versus 8-bit. Pick the highest quantization that still fits in your VRAM.