Run LiquidAI/LFM2.5-8B-A1B-GGUF locally
LiquidAI/LFM2.5-8B-A1B-GGUF is a large language model with 8.47 billion parameters, built on the lfm2moe architecture. It is released under the other license and has been downloaded 187,510 times.
To run LiquidAI/LFM2.5-8B-A1B-GGUF locally at a 4,096-token context, its quantized versions need between 6.72 GB (Q4_0, lowest quality) and 17.99 GB (BF16, highest quality) of memory, weights plus KV cache and a system margin included.
For most users the best balance is Q5_K_M, needing about 7.82 GB. That means LiquidAI/LFM2.5-8B-A1B-GGUF fits entirely in the VRAM of an 8 GB GPU or larger, running fully on the GPU.
All quantizations
| Quant. | Bits | Quality | Weights | KV | Total | Speed~ | Verdict |
|---|---|---|---|---|---|---|---|
| Q4_0 | 4.58 | Good | 4.51 GB | 1.4 GB | 6.72 GB | 88.7 t/s | Fits in VRAM |
| Q4_K_M | 4.87 | Good | 4.8 GB | 1.4 GB | 7.01 GB | 83.3 t/s | Fits in VRAM |
| Q5_K_M | 5.7 | Very good | 5.62 GB | 1.4 GB | 7.82 GB | 71.2 t/s | Fits in VRAM |
| Q6_K | 6.58 | Excellent | 6.48 GB | 1.4 GB | 8.69 GB | 7.7 t/s | Offload |
| Q8_0 | 8.51 | Excellent | 8.39 GB | 1.4 GB | 10.6 GB | 6.0 t/s | Offload |
| BF16 | 16.01 | Excellent | 15.78 GB | 1.4 GB | 17.99 GB | 3.2 t/s | Offload |
| F16 | 16.01 | Excellent | 15.78 GB | 1.4 GB | 17.99 GB | 3.2 t/s | Offload |
KV cache estimated (architecture unavailable). Speed is a rough estimate bounded by memory bandwidth.
Frequently asked questions
How much VRAM do you need to run LiquidAI/LFM2.5-8B-A1B-GGUF?
You need about 7.82 GB of VRAM to run LiquidAI/LFM2.5-8B-A1B-GGUF entirely on the GPU using the Q5_K_M quantization (at a 4,096-token context). Smaller quantizations lower the requirement at the cost of quality.
Can I run LiquidAI/LFM2.5-8B-A1B-GGUF on an 8 GB GPU?
Yes. With 8 GB of VRAM you can run LiquidAI/LFM2.5-8B-A1B-GGUF fully on the GPU using Q5_K_M (about 7.82 GB).
Can I run LiquidAI/LFM2.5-8B-A1B-GGUF on a 16 GB GPU?
Yes. With 16 GB of VRAM you can run LiquidAI/LFM2.5-8B-A1B-GGUF fully on the GPU using Q8_0 (about 10.6 GB).
Can I run LiquidAI/LFM2.5-8B-A1B-GGUF on a 24 GB GPU?
Yes. With 24 GB of VRAM you can run LiquidAI/LFM2.5-8B-A1B-GGUF fully on the GPU using BF16 (about 17.99 GB).
What is the best quantization for LiquidAI/LFM2.5-8B-A1B-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.