LFM2 2.6B Longevity — Hardware Requirements & GPU Compatibility
Chat
LFM2 2.6B Longevity is a 2.6B-parameter open language model from Liquid AI in the LFM2 family. It supports a context window of up to 128,000 tokens. At Q4_K_M it needs about 1.97 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 125K)Best on 24 GB (Q4_K_M · ~333 tok/s · 125K)Macs from 8 GB (Q4_K_M · ~36 tok/s)
Other
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run LFM2 2.6B Longevity
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve LiquidAI/LFM2-2.6B-Longevity --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (9 GB headroom) · Q4_K_M
- Generation speed
- ~119 tok/s
- generation speed
- Cost per 1M output tokens
- $0.19
- per 1M output tokens
How Much VRAM Does LFM2 2.6B Longevity Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 1.5 GB | 2.2 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 125K context · ~431 tok/s | |
| 1.7 GB | 2.4 GB | 3-bit medium — 3-bit medium quantization | Fits: 125K context · ~390 tok/s | |
| 2.0 GB | 2.7 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 125K context · ~333 tok/s | |
| 2.3 GB | 2.9 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 125K context · ~290 tok/s | |
| 2.5 GB | 3.2 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 125K context · ~257 tok/s | |
| 3 GB | 3.7 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 125K context · ~218 tok/s | |
| 5.6 GB | 6.2 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 125K context · ~118 tok/s |
Selected Q4_K_M
4-bit medium quantization2.3GBat 16K context
- Weights
- 1.5 GB
- KV cache
- 0.4 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 21.8 GB free · ~333 tok/s
≥50 tok/s needs ≥151 GB/s · RTX 5090 ~591, RTX 3090 Ti ~333
Which Hardware Can Run LFM2 2.6B Longevity?
Q4_K_M · 2.0 GBLFM2 2.6B Longevity (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 128K context window can add up to 3.0 GB, bringing total usage to 5.0 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run LFM2 2.6B Longevity, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 5.8 GB free · up to 125K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~251Simulate output on RTX 3080RTX 2080 Ti~203Simulate output on RTX 2080 TiRTX 3070 Ti~201Simulate output on RTX 3070 TiM3*8 GB~36Simulate output on iMac 24" M3 (8 GB)Orin Nano~34Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~24Simulate output on iPhone 1720 GB
fits · 17.8 GB free · up to 125K ctx
1 GPU
RX 7900 XT~244Simulate output on RX 7900 XT32–40 GB
fits · 29.8 GB free · up to 125K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~591Simulate output on RTX 5090M5 Max36 GB~164Simulate output on Mac Studio M5 Max (36 GB)M532 GB~55Simulate output on MacBook Air 13" M5 (32 GB)Orin~68Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~45Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to LFM2 2.6B Longevity
LFM2 family · 9 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| MiniCPM5 2BOpenBMB | — | 2.5 GB | ~345 | same size |
| North Micro Vision InstructCohere | — | 7.1 GB | ~119 | same size |
| Granite 3.1 2B InstructIBM | — | 3.2 GB | ~329 | same size |
| Gemma 2 2B ITGoogle | — | 2.5 GB | ~379 | same size |
| Ouro 2.6B ThinkingByteDance | — | 12.1 GB | ~102 | same size |
| Nemotron Flash 3BNVIDIA | — | 7.6 GB | ~109 | same size |
Specifications
- Publisher
- Liquid AI
- Family
- LFM2
- Parameters
- 2.6B
- Architecture
- Lfm2ForCausalLM
- Context Length
- 128,000 tokens
- Vocabulary Size
- 65,536
- Release Date
- 2026-05-25
- License
- Other
Frequently Asked Questions
How much VRAM does LFM2 2.6B Longevity need?
LFM2 2.6B Longevity requires 2.0 GB of VRAM at Q4_K_M, or 5.6 GB at BF16. Full 128K context adds up to 3.0 GB (5.0 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 2.6B × 4.8 bits ÷ 8 = 1.5 GB
KV Cache + Overhead ≈ 0.5 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 3.5 GB (at full 128K context)
VRAM usage by quantization
What's the best quantization for LFM2 2.6B Longevity?
For LFM2 2.6B Longevity, Q4_K_M (2.0 GB) offers the best balance of quality and VRAM usage. Q5_K_M (2.3 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 1.5 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run LFM2 2.6B Longevity on a Mac?
Yes — Mac Mini M2 (8 GB) and 145 other Macs can run LFM2 2.6B Longevity. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 2.0 GB of usable unified memory (RAM minus macOS overhead).
Can I run LFM2 2.6B Longevity locally?
Yes — LFM2 2.6B Longevity can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is LFM2 2.6B Longevity?
At Q4_K_M, LFM2 2.6B Longevity can reach ~2437 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~333 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 ÷ 1.97 × 0.65 = ~2640 tok/s
Estimated speed at Q4_K_M (2.0 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of LFM2 2.6B Longevity?
At Q4_K_M, the download is about 1.54 GB. The full-precision BF16 version is 5.14 GB. The smallest option (Q2_K) is 1.09 GB.
Which GPUs can run LFM2 2.6B Longevity?
52 consumer GPUs can run LFM2 2.6B Longevity at Q4_K_M. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
Which devices can run LFM2 2.6B Longevity?
163 devices with unified memory can run LFM2 2.6B Longevity at Q4_K_M (2.0 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (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.