llmrun
Liquid AILFM2.5Lfm2VlForConditionalGeneration

LFM2.5 VL 450M — Hardware Requirements & GPU Compatibility

VisionFunctions

LFM2.5-VL-450M is Liquid AI's vision-language model with 450 million parameters, representing an update to LFM2-VL-450M that uses the LFM2.5-350M backbone plus an 86-million-parameter SigLIP2 vision encoder. The card notes gains in instruction following, stronger multilingual vision understanding across nine languages, bounding box prediction for object detection, and function calling when given text-only input. Images as large as 512x512 are handled natively; larger ones get tiled. Built for edge devices, this size runs on a phone, a CPU, or any modest GPU, while Liquid AI also provides a WebGPU browser demo. The card specifies a context length of 32,768 tokens. It comes under Liquid AI's LFM1.0 license, which is custom rather than a standard open-source one, so you should check its terms before commercial use. The model was published in April 2026 as an updated version of the earlier LFM2-VL-450M.

449M params · dense128K contextOther42.9K downloads238 likes23.9K quant downloads
Based on LFM2.5 350M
S

Runs great on a 24 GB GPU

Runs from8 GB Q4_K_M · 125KBest on24 GB Q4_K_M · ~1024 tok/s · 125KMacs from8 GB Q4_K_M · ~112 tok/s

Other

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

Run LFM2.5 VL 450M

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
one command · needs Ollama installed
$ollama run hf.co/LiquidAI/LFM2.5-VL-450M-GGUF:Q4_K_M

Q4_K_M fits fully on the RTX 4090 · 23.2 GB free · 16K context

Download: LFM2.5-VL-450M-Q4_K_M.gguf0.23 GBLiquidAI

install, OS, other quants

Ways to runOther ways

each opens step-by-step

Run 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

How Much VRAM Does LFM2.5 VL 450M Need?

Select a quantization level; the listed hardware adheres to it.

QuantizationVRAM+32KOn RTX 4090 (reference)
0.6 GB1 GB2-bit · K-quant — 2-bit quantization with K-quant improvementsFits: 125K context · ~1170 tok/s
0.6 GB1 GB3-bit medium — 3-bit medium quantizationFits: 125K context · ~1111 tok/s
0.6 GB1 GB4-bit · legacy — 4-bit legacy quantizationFits: 125K context · ~1111 tok/s
0.6 GB1 GB4-bit medium — 4-bit medium quantization — most popular sweet spotFits: 125K context · ~1024 tok/s
0.7 GB1.1 GB5-bit medium — 5-bit medium quantization — good quality/size tradeoffFits: 125K context · ~950 tok/s
0.7 GB1.1 GB6-bit, very good — 6-bit quantization, very good qualityFits: 125K context · ~885 tok/s
0.8 GB1.2 GB8-bit, near-lossless — 8-bit quantization, near-losslessFits: 125K context · ~799 tok/s
1.3 GB1.7 GB16-bit · bfloat — Brain floating point 16 — preferred for trainingFits: 125K context · ~520 tok/s
est.calculated, no published file yet

Selected Q4_K_M

4-bit medium quantization

0.8GBat 16K context

Weights
0.3 GB
KV cache
0.2 GB
Overhead
0.3 GB

Fits RTX 4090 (reference) · 23.2 GB free · ~1024 tok/s

≥50 tok/s needs ≥49 GB/s · RTX 5090 ~1820, M5 Ultra ~1343

Which Hardware Can Run LFM2.5 VL 450M?

Q4_K_M · 0.6 GB

LFM2.5 VL 450M (Q4_K_M) requires 0.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1+ GB is recommended. Using the full 128K context window can add up to 1.8 GB, bringing total usage to 2.4 GB. 114 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 185 devices with unified memory can run LFM2.5 VL 450M, including Mac Studio M5 Ultra (256 GB), Mac Studio M5 Ultra (512 GB).

By VRAM tier · typical GPUs and Macs at Q4_K_M
8 GB · RTX 4060Q4_K_M · 0.8 GB · ~276 tok/s · 125K8 GB tier →
12 GB · RTX 3060 12GBQ4_K_M · 0.8 GB · ~366 tok/s · 125K12 GB tier →
16 GB · RTX 5060 Ti 16GBQ4_K_M · 0.8 GB · ~455 tok/s · 125K16 GB tier →
24 GB · RTX 4090referenceQ4_K_M · 0.8 GB · ~1024 tok/s · 125K24 GB tier →
Mac 32 GB · Mac Mini M4Q4_K_M · 0.8 GB · ~131 tok/s · 125KMacs →
Mac 64 GB · Mac Studio M4 MaxQ4_K_M · 0.8 GB · ~597 tok/s · 125KMacs →

Alternatives to LFM2.5 VL 450M

LFM2.5 family · 15 models →

Similar models

1
ModelScoreVRAMtok/sWhy it is similar
Gemma 4 26B A4B IT DFlashz-lab—0.8 GB~1111same size

Specifications

Publisher
Liquid AI
Family
LFM2.5
Parameters
449M
Architecture
Lfm2VlForConditionalGeneration
Context Length
128,000 tokens
Vocabulary Size
65,536
Release Date
2026-04-08
License
Other

Frequently Asked Questions

How much VRAM does LFM2.5 VL 450M need?

LFM2.5 VL 450M requires 0.6 GB of VRAM at Q4_K_M, or 1.3 GB at BF16. Full 128K context adds up to 1.8 GB (2.4 GB total).

VRAM = Weights + KV Cache + Overhead

Weights = 449M × 4.8 bits ÷ 8 = 0.3 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

0.6 GB
2.4 GB

Learn more about VRAM estimation →

What's the best quantization for LFM2.5 VL 450M?

For LFM2.5 VL 450M, Q4_K_M (0.6 GB) offers the best balance of quality and VRAM usage. Q5_K_M (0.7 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 0.6 GB.

VRAM requirement by quantization

Q2_K
0.6 GB
Q4_0
0.6 GB
Q4_K_M ★
0.6 GB
Q5_K_M
0.7 GB
Q6_K
0.7 GB
BF16
1.3 GB

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

Can I run LFM2.5 VL 450M on a Mac?

Yes — MacBook Air 13" M3 (8 GB) and 158 other Macs can run LFM2.5 VL 450M. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 0.6 GB of usable unified memory (RAM minus macOS overhead).

Can I run LFM2.5 VL 450M locally?

Yes — LFM2.5 VL 450M can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is LFM2.5 VL 450M?

At Q4_K_M, LFM2.5 VL 450M can reach ~7500 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~1024 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 ÷ 0.64 × 0.65 = ~8125 tok/s

Estimated speed at Q4_K_M (0.6 GB)

~8125 tok/s
~1024 tok/s
~8125 tok/s
~7500 tok/s

Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.

Learn more about tok/s estimation →

What's the download size of LFM2.5 VL 450M?

At Q4_K_M, the download is about 0.27 GB. The full-precision BF16 version is 0.90 GB. The smallest option (Q2_K) is 0.19 GB.

Which GPUs can run LFM2.5 VL 450M?

114 consumer GPUs can run LFM2.5 VL 450M at Q4_K_M. Top options include AMD Radeon RX 5600 XT, AMD Radeon RX 5700 XT, AMD Radeon RX 580 8GB. 114 GPUs have plenty of headroom for comfortable inference.

Which devices can run LFM2.5 VL 450M?

185 devices with unified memory can run LFM2.5 VL 450M at Q4_K_M (0.6 GB), including AMD Ryzen 7 8845HS (Hawk Point) Laptop, AMD Ryzen AI 7 350 (Krackan Point) Laptop, AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10. Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.