LFM2.5 2.6B — Hardware Requirements & GPU Compatibility
Chat
LFM2.5 2.6B is a 2.7B-parameter open language model from Liquid AI in the LFM2.5 family. It supports a context window of up to 131,072 tokens. At Q4_K_M it needs about 2.04 GB of VRAM — see which GPUs and Macs can run it below.
131.3K downloads
735 likesSpecifications
- Publisher
- Liquid AI
- Family
- LFM2.5
- Parameters
- 2.7B
- Architecture
- Lfm2ForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 128,000
- Release Date
- 2026-07-28
- License
- Other
Get Started
HuggingFace
How Much VRAM Does LFM2.5 2.6B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 1.6 GB | 9.5 GB | 1.15 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 1.6 GB | 9.5 GB | 1.18 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 1.7 GB | 9.7 GB | 1.31 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 1.8 GB | 9.7 GB | 1.35 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 2.0 GB | 10.0 GB | 1.62 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 2.4 GB | 10.3 GB | 1.92 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 2.6 GB | 10.6 GB | 2.23 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 3.1 GB | 11.1 GB | 2.70 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run LFM2.5 2.6B?
Q4_K_M · 2.0 GBLFM2.5 2.6B (Q4_K_M) requires 2.0 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 3+ GB is recommended. Using the full 131K context window can add up to 7.9 GB, bringing total usage to 10.0 GB. 50 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run LFM2.5 2.6B?
Q4_K_M · 2.0 GB59 devices with unified memory can run LFM2.5 2.6B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomWhere to Download LFM2.5 2.6B
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Related Models
Frequently Asked Questions
- How much VRAM does LFM2.5 2.6B need?
LFM2.5 2.6B requires 2.0 GB of VRAM at Q4_K_M, or 5.8 GB at BF16. Full 131K context adds up to 7.9 GB (10.0 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 2.7B × 4.8 bits ÷ 8 = 1.6 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 8.4 GB (at full 131K context)
VRAM usage by quantization
Q4_K_M2.0 GBQ4_K_M + full context10.0 GB- What's the best quantization for LFM2.5 2.6B?
For LFM2.5 2.6B, Q4_K_M (2.0 GB) offers the best balance of quality and VRAM usage. Q4_K_L (2.1 GB) provides better quality if you have the VRAM. The smallest option is IQ2_M at 1.3 GB.
VRAM requirement by quantization
IQ2_M1.3 GBIQ3_M1.6 GBQ4_K_S1.9 GBQ4_K_M ★2.0 GBQ5_K_S2.3 GBBF165.8 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run LFM2.5 2.6B on a Mac?
LFM2.5 2.6B requires at least 1.3 GB at IQ2_M, 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 2.6B locally?
Yes — LFM2.5 2.6B can run locally on consumer hardware. At Q4_K_M quantization it needs 2.0 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is LFM2.5 2.6B?
At Q4_K_M, LFM2.5 2.6B can reach ~2353 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~321 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 ÷ 2.0 × 0.65 = ~2549 tok/s
Estimated speed at Q4_K_M (2.0 GB)
~2549 tok/s~321 tok/s~2549 tok/s~2353 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 2.6B?
At Q4_K_M, the download is about 1.62 GB. The full-precision BF16 version is 5.39 GB. The smallest option (IQ2_M) is 0.91 GB.
- Which GPUs can run LFM2.5 2.6B?
50 consumer GPUs can run LFM2.5 2.6B at Q4_K_M (2.0 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 50 GPUs have plenty of headroom for comfortable inference.
- Which devices can run LFM2.5 2.6B?
59 devices with unified memory can run LFM2.5 2.6B at Q4_K_M (2.0 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.