LFM2 VL 1.6B — Hardware Requirements & GPU Compatibility
Vision
LFM2-VL-1.6B is Liquid AI's 1.6-billion-parameter vision-language model, pairing a hybrid convolution-and-attention LFM2 language backbone (1.2B parameters) with a 400-million-parameter SigLIP2 NaFlex vision encoder. It targets image understanding and lightweight agentic tasks with variable-resolution inputs, tuned for low latency over heavy reasoning; Liquid AI recommends fine-tuning it for narrow use cases. It is small enough to run on a single modest consumer GPU. The model supports a 128,000 token context window. It is released under Liquid AI's LFM Open License v1.0, free including for commercial use under $10 million in annual revenue, above which a separate license applies. Published in August 2025 alongside a smaller 450M sibling, it claims roughly 2x faster GPU inference than comparable models while handling native 512x512 resolution without upscaling.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 125K)Best on 24 GB (Q4_K_M · ~496 tok/s · 125K)Macs from 8 GB (Q4_K_M · ~54 tok/s)
Other
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run LFM2 VL 1.6B
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
ollama run hf.co/bartowski/LiquidAI_LFM2-VL-1.6B-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 22.5 GB free · 16K context
Download: LiquidAI_LFM2-VL-1.6B-Q4_K_M.gguf0.73 GBbartowski
Ways to runOther ways
each opens step-by-stepRun in cloud
Your own private copy · Q4_K_M · 24 GB GPU
- The easiest way to try this model
- Running in a few minutes, easy setup
- Chat right here or connect any app
$5+ bonus for new users
Runs on RTX 3080 Ti (12 GB) (10 GB headroom) · Q4_K_M
- Generation speed
- ~449 tok/s
- generation speed
- Cost per 1M output tokens
- $0.076
- per 1M output tokens
How Much VRAM Does LFM2 VL 1.6B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 1.0 GB | 1.4 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 125K context · ~630 tok/s | |
| 1.1 GB | 1.5 GB | 3-bit small — 3-bit small quantization | Fits: 125K context · ~618 tok/s | |
| 1.1 GB | 1.5 GB | 3-bit medium — 3-bit medium quantization | Fits: 125K context · ~575 tok/s | |
| 1.2 GB | 1.6 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 125K context · ~565 tok/s | |
| 1.3 GB | 1.7 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 125K context · ~496 tok/s | |
| 1.5 GB | 1.9 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 125K context · ~437 tok/s | |
| 1.7 GB | 2.1 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 125K context · ~392 tok/s | |
| 1.9 GB | 2.4 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 125K context · ~336 tok/s |
Selected Q4_K_M
4-bit medium quantization1.5GBat 16K context
- Weights
- 1.0 GB
- KV cache
- 0.2 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 22.5 GB free · ~496 tok/s
≥50 tok/s needs ≥101 GB/s · RTX 5090 ~882, RTX 3090 Ti ~496
Which Hardware Can Run LFM2 VL 1.6B?
Q4_K_M · 1.3 GBLFM2 VL 1.6B (Q4_K_M) requires 1.3 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 2+ GB is recommended. Using the full 128K context window can add up to 1.8 GB, bringing total usage to 3.1 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run LFM2 VL 1.6B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 6.5 GB free · up to 125K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~374Simulate output on RTX 3080RTX 2080 Ti~303Simulate output on RTX 2080 TiRTX 3070 Ti~300Simulate output on RTX 3070 TiM3*8 GB~54Simulate output on iMac 24" M3 (8 GB)Orin Nano~50Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~36Simulate output on iPhone 1720 GB
fits · 18.5 GB free · up to 125K ctx
1 GPU
RX 7900 XT~364Simulate output on RX 7900 XT32–40 GB
fits · 30.5 GB free · up to 125K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~882Simulate output on RTX 5090M5 Max36 GB~244Simulate output on Mac Studio M5 Max (36 GB)M532 GB~82Simulate output on MacBook Air 13" M5 (32 GB)Orin~101Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~67Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to LFM2 VL 1.6B
LFM2 family · 9 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| MiniCPM V 4.7 1BOpenBMB | — | 1.6 GB | ~512 | same size |
| Granite 4.0 1BIBM | — | 2.6 GB | ~452 | same size |
| Qwen Base Invoicev1.01 1.5BLaaP-ai | — | 1.7 GB | ~512 | same size |
| OLMo 2 0425 1B InstructAllen AI | — | 1.7 GB | ~449 | same size |
| OpenMath Nemotron 1.5BNVIDIA | — | 1.7 GB | ~512 | same size |
| ReaderLM v2jinaai | — | 1.7 GB | ~512 | same size |
Specifications
- Publisher
- Liquid AI
- Family
- LFM2
- Parameters
- 1.6B
- Architecture
- Lfm2VlForConditionalGeneration
- Context Length
- 128,000 tokens
- Vocabulary Size
- 65,536
- Release Date
- 2025-08-12
- License
- Other
Frequently Asked Questions
How much VRAM does LFM2 VL 1.6B need?
LFM2 VL 1.6B requires 1.3 GB of VRAM at Q4_K_M, or 3.5 GB at BF16. Full 128K context adds up to 1.8 GB (3.1 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 1.6B × 4.8 bits ÷ 8 = 1 GB
KV Cache + Overhead ≈ 0.3 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 ≈ 2.1 GB (at full 128K context)
VRAM usage by quantization
What's the best quantization for LFM2 VL 1.6B?
For LFM2 VL 1.6B, Q4_K_M (1.3 GB) offers the best balance of quality and VRAM usage. Q4_K_L (1.3 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 0.8 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run LFM2 VL 1.6B on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run LFM2 VL 1.6B. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 1.3 GB of usable unified memory (RAM minus macOS overhead).
Can I run LFM2 VL 1.6B locally?
Yes — LFM2 VL 1.6B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is LFM2 VL 1.6B?
At Q4_K_M, LFM2 VL 1.6B can reach ~3636 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~496 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 ÷ 1.32 × 0.65 = ~3939 tok/s
Estimated speed at Q4_K_M (1.3 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of LFM2 VL 1.6B?
At Q4_K_M, the download is about 0.95 GB. The full-precision BF16 version is 3.17 GB. The smallest option (IQ2_XXS) is 0.44 GB.
Which GPUs can run LFM2 VL 1.6B?
52 consumer GPUs can run LFM2 VL 1.6B 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 VL 1.6B?
163 devices with unified memory can run LFM2 VL 1.6B at Q4_K_M (1.3 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.