LFM2.5 1.2B Instruct GGUF — Hardware Requirements & GPU Compatibility
Chat
This is the GGUF-quantized release of Liquid AI's LFM2.5 1.2B Instruct, packaged for easy local inference with llama.cpp and compatible tools. At 1.2 billion parameters, the quantized versions are tiny enough to run on almost anything, from a Raspberry Pi to a basic laptop. GGUF quantization at various bit levels lets users choose their preferred tradeoff between quality and size, making this one of the most hardware-friendly models available for quick local experimentation.
59.3K downloads
141 likesSpecifications
- Publisher
- LiquidAI
- Parameters
- 1.2B
- Release Date
- 2026-01-05
- License
- Other
Get Started
HuggingFace
How Much VRAM Does LFM2.5 1.2B Instruct GGUF Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q4_0 | 4.00 | 0.7 GB | — | 0.60 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 0.8 GB | — | 0.72 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 0.9 GB | — | 0.85 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 1.1 GB | — | 0.99 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 1.3 GB | — | 1.20 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run LFM2.5 1.2B Instruct GGUF?
Q4_K_M · 0.8 GBLFM2.5 1.2B Instruct GGUF (Q4_K_M) requires 0.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 2+ GB is recommended. 35 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run LFM2.5 1.2B Instruct GGUF?
Q4_K_M · 0.8 GB33 devices with unified memory can run LFM2.5 1.2B Instruct GGUF, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does LFM2.5 1.2B Instruct GGUF need?
LFM2.5 1.2B Instruct GGUF requires 0.8 GB of VRAM at Q4_K_M, or 1.3 GB at Q8_0.
VRAM = Weights + KV Cache + Overhead
Weights = 1.2B × 4.8 bits ÷ 8 = 0.7 GB
KV Cache + Overhead ≈ 0.1 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
Q4_K_M0.8 GB- What's the best quantization for LFM2.5 1.2B Instruct GGUF?
For LFM2.5 1.2B Instruct GGUF, Q4_K_M (0.8 GB) offers the best balance of quality and VRAM usage. Q5_K_M (0.9 GB) provides better quality if you have the VRAM. The smallest option is Q4_0 at 0.7 GB.
VRAM requirement by quantization
Q4_00.7 GB~85%Q4_K_M ★0.8 GB~89%Q5_K_M0.9 GB~92%Q6_K1.1 GB~95%Q8_01.3 GB~99%★ Recommended — best balance of quality and VRAM usage.
- Can I run LFM2.5 1.2B Instruct GGUF on a Mac?
LFM2.5 1.2B Instruct GGUF requires at least 0.7 GB at Q4_0, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run LFM2.5 1.2B Instruct GGUF locally?
Yes — LFM2.5 1.2B Instruct GGUF can run locally on consumer hardware. At Q4_K_M quantization it needs 0.8 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is LFM2.5 1.2B Instruct GGUF?
At Q4_K_M, LFM2.5 1.2B Instruct GGUF can reach ~3690 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~829 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 0.8 × 0.55 = ~3690 tok/s
Estimated speed at Q4_K_M (0.8 GB)
AMD Instinct MI300X~3690 tok/sNVIDIA GeForce RTX 4090~829 tok/sNVIDIA H100 SXM~2758 tok/sAMD Instinct MI250X~2281 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of LFM2.5 1.2B Instruct GGUF?
At Q4_K_M, the download is about 0.72 GB. The full-precision Q8_0 version is 1.20 GB. The smallest option (Q4_0) is 0.60 GB.