LFM2.5 1.2B Thinking — Hardware Requirements & GPU Compatibility
Chat
33.2K downloads
312 likesSpecifications
- Publisher
- LiquidAI
- Parameters
- 1.2B
- Architecture
- Lfm2ForCausalLM
- Context Length
- 128,000 tokens
- Vocabulary Size
- 65,536
- Release Date
- 2026-02-02
- License
- Other
Get Started
HuggingFace
How Much VRAM Does LFM2.5 1.2B Thinking Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 2.8 GB | 6.9 GB | 2.40 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run LFM2.5 1.2B Thinking?
BF16 · 2.8 GBLFM2.5 1.2B Thinking (BF16) requires 2.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 4+ GB is recommended. Using the full 128K context window can add up to 4.1 GB, bringing total usage to 6.9 GB. 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 Thinking?
BF16 · 2.8 GB33 devices with unified memory can run LFM2.5 1.2B Thinking, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomRelated Models
Derivatives (1)
Frequently Asked Questions
- How much VRAM does LFM2.5 1.2B Thinking need?
LFM2.5 1.2B Thinking requires 2.8 GB of VRAM at BF16. Full 128K context adds up to 4.1 GB (6.9 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 1.2B × 16 bits ÷ 8 = 2.4 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 4.5 GB (at full 128K context)
VRAM usage by quantization
BF162.8 GBBF16 + full context6.9 GB- Can I run LFM2.5 1.2B Thinking on a Mac?
LFM2.5 1.2B Thinking requires at least 2.8 GB at BF16, 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 Thinking locally?
Yes — LFM2.5 1.2B Thinking can run locally on consumer hardware. At BF16 quantization it needs 2.8 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is LFM2.5 1.2B Thinking?
At BF16, LFM2.5 1.2B Thinking can reach ~1052 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~237 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 ÷ 2.8 × 0.55 = ~1052 tok/s
Estimated speed at BF16 (2.8 GB)
AMD Instinct MI300X~1052 tok/sNVIDIA GeForce RTX 4090~237 tok/sNVIDIA H100 SXM~787 tok/sAMD Instinct MI250X~651 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 Thinking?
At BF16, the download is about 2.40 GB.
- Which GPUs can run LFM2.5 1.2B Thinking?
35 consumer GPUs can run LFM2.5 1.2B Thinking at BF16 (2.8 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 35 GPUs have plenty of headroom for comfortable inference.
- Which devices can run LFM2.5 1.2B Thinking?
33 devices with unified memory can run LFM2.5 1.2B Thinking at BF16 (2.8 GB), including Mac Mini M4 (16 GB), Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.