LFM2 8B A1B — Hardware Requirements & GPU Compatibility
Chat
LFM2 8B A1B is Liquid AI's larger mixture-of-experts model, combining the company's novel hybrid architecture with approximately 8 billion total parameters. It uses a MoE design to keep active compute per token low while maintaining strong general performance across chat and reasoning tasks. For local users, it offers an intriguing alternative to conventional 8B transformers, with Liquid AI's architecture promising improved efficiency and throughput on consumer-grade hardware.
46.0K downloads
367 likesSpecifications
- Publisher
- LiquidAI
- Parameters
- 8.3B
- Architecture
- Lfm2MoeForCausalLM
- Context Length
- 128,000 tokens
- Vocabulary Size
- 65,536
- Release Date
- 2025-10-07
- License
- Other
Get Started
HuggingFace
How Much VRAM Does LFM2 8B A1B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 4.0 GB | 10.1 GB | 3.54 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 4.0 GB | 10.2 GB | 3.65 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 4.5 GB | 10.7 GB | 4.07 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 4.6 GB | 10.8 GB | 4.17 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 5.4 GB | 11.6 GB | 5.00 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 6.3 GB | 12.5 GB | 5.94 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 7.3 GB | 13.5 GB | 6.88 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 8.7 GB | 14.9 GB | 8.34 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run LFM2 8B A1B?
Q4_K_M · 5.4 GBLFM2 8B A1B (Q4_K_M) requires 5.4 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 8+ GB is recommended. Using the full 128K context window can add up to 6.2 GB, bringing total usage to 11.6 GB. 50 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3070 Ti.
Runs great
— Plenty of headroom
Decent
— Enough VRAM, may be tightWhich Devices Can Run LFM2 8B A1B?
Q4_K_M · 5.4 GB58 devices with unified memory can run LFM2 8B A1B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, MacBook Air 13" M3 (8 GB).
Runs great
— Plenty of headroomWhere to Download LFM2 8B A1B
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Frequently Asked Questions
- How much VRAM does LFM2 8B A1B need?
LFM2 8B A1B requires 5.4 GB of VRAM at Q4_K_M, or 17.1 GB at BF16. Full 128K context adds up to 6.2 GB (11.6 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 8.3B × 4.8 bits ÷ 8 = 5 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 6.6 GB (at full 128K context)
VRAM usage by quantization
Q4_K_M5.4 GBQ4_K_M + full context11.6 GB- What's the best quantization for LFM2 8B A1B?
For LFM2 8B A1B, Q4_K_M (5.4 GB) offers the best balance of quality and VRAM usage. Q5_0 (5.6 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 2.7 GB.
VRAM requirement by quantization
IQ2_XXS2.7 GBIQ3_S4.0 GBIQ4_XS4.9 GBQ4_K_M ★5.4 GBQ5_05.6 GBBF1617.1 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run LFM2 8B A1B on a Mac?
LFM2 8B A1B requires at least 2.7 GB at IQ2_XXS, 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 8B A1B locally?
Yes — LFM2 8B A1B can run locally on consumer hardware. At Q4_K_M quantization it needs 5.4 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is LFM2 8B A1B?
At Q4_K_M, LFM2 8B A1B can reach ~815 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~121 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 5.4 × 0.65 = ~963 tok/s
Estimated speed at Q4_K_M (5.4 GB)
~963 tok/s~121 tok/s~963 tok/s~815 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of LFM2 8B A1B?
At Q4_K_M, the download is about 5.00 GB. The full-precision BF16 version is 16.68 GB. The smallest option (IQ2_XXS) is 2.29 GB.
- Which GPUs can run LFM2 8B A1B?
50 consumer GPUs can run LFM2 8B A1B at Q4_K_M (5.4 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 7600. 39 GPUs have plenty of headroom for comfortable inference.
- Which devices can run LFM2 8B A1B?
59 devices with unified memory can run LFM2 8B A1B at Q4_K_M (5.4 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Apple iPhone 17 Pro, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.