Can I run LFM3-1.7B on an RTX 4060 Ti 16GB?
Key facts
Yes. LFM3-1.7B runs on an RTX 4060 Ti 16GB, about 179 tokens per second (tok/s).
It needs about 2.0 GB at standard quality (estimate). Checked . LiquidAI Q4_K_M GGUF.
The cheapest graphics card on our list that holds it at Q4 is the GeForce RTX 3060 12GB. On an RTX 4060 Ti 16GB, at 32,768 tokens of context, it still fits in graphics memory (estimate).
Updated · LFM3-1.7B on every card
How much memory it needs
It uses about 13% of the memory that is free on this card.
Get a 1-line alert when a faster quant for LFM3-1.7B drops — or when GPUs that run it drop >10%
Get a 1-line alert when a new open-weight model fits 8 GB VRAM (2.0 GB at Q4 for LFM3-1.7B) or when used RTX 3090 / 4090 & Mac Studio prices drop >10% — weekly, zero spam.
What an RTX 4060 Ti 16GB costs
GeForce RTX 4060 Ti 16GB$832€899new (lowest in-stock EU)
EU shops · Shown to visitors in Europe.US shops · Shown to visitors outside Europe.
We never pass off an estimate as a benchmark. Commissions never change which hardware we recommend. How we calculate
Price details
$832€899
How we priced this
New price, the lowest in stock in the EU.
Source: GPU PRIX, checked 16 Oct 2026.
Lowest new price in stock on 16 Oct 2026: €899, an MSI Gaming X Slim 16GB from the Netherlands. Over the past 3 months the typical price was €629.
Prices excl. shipping unless marked. Euro prices incl. VAT where the seller charges it. Dollar prices are converted from our euro prices without the 21% EU VAT, before US sales tax.
The cheapest graphics card on our list that also runs it (it still needs the rest of a PC): GeForce RTX 3060 12GB, $292€261, used (median of sold listings). Fast~222 tok/s
The cheapest complete machine that runs it: Mac mini M4 16GB, about $615€549 (used). Fast~47 tok/s
If you buy through these links we may earn a commission. It doesn't change our ranking. How shop links work
As an Amazon Associate I earn from qualifying purchases.
Als Amazon-Partner verdiene ich an qualifizierten Verkäufen.
Als Amazon-Partner verdien ik aan in aanmerking komende aankopen.
LFM3-1.7B on other graphics cards
Runs well10
The whole model fits in the graphics memory.
More about the model itself, what it is good at and its licence: LFM3-1.7B.
The numbers behind this answer
A model comes in several sizes. Q4 is the standard one most people use; the bigger ones answer a little better but need more memory. Each row adds up the model file, the memory a conversation takes, and some working space, and compares the total with what is free on this card.
Swipe the table sideways to see every column.
| Quality | Conversation | Result | Speed | Model file | Conversation memory | Working space | Total needed | Free memory |
|---|---|---|---|---|---|---|---|---|
| Q4 · standard (smallest that keeps quality) | ~12 pages8,192 tokens | Runs | Fast~179 tok/s | 1.1 GBmeasured file | 0.1 GB | 0.8 GB | 2.0 GB | 15.4 GB |
| Q5 · a bit sharper, a bit bigger | ~12 pages8,192 tokens | Runs | Fast~162 tok/s | 1.2 GB | 0.1 GB | 0.8 GB | 2.1 GB | 15.4 GB |
| Q8 · near full quality, almost twice Q4 | ~12 pages8,192 tokens | Runs | Fast~112 tok/s | 1.9 GB | 0.1 GB | 0.8 GB | 2.8 GB | 15.4 GB |
| FP16 · full quality, over three times Q4 | ~12 pages8,192 tokens | Runs | Fast~62 tok/s | 3.5 GB | 0.1 GB | 0.8 GB | 4.4 GB | 15.4 GB |
| Q4 · standard, longer conversation | ~49 pages32,768 tokens | Runs | Fast~144 tok/s | 1.1 GBmeasured file | 0.4 GB | 0.8 GB | 2.3 GB | 15.4 GB |
Sources and method
Memory and speed on this page are our estimate, not a measured test. Checked . LiquidAI Q4_K_M GGUF.
Dense text model for local agents, 1.73B parameters. Hugging Face safetensors metadata lists 1,728,801,536 parameters, all BF16. 1.73B is that count to two decimals, so our parameter count is an estimate. The model card also states 1.73B. Architecture Lfm3ForCausalLM (model type lfm3): 24 layers, 13 gated short convolutions, 5 sliding-window attention layers with a 256-token window and 6 global attention layers, 4 KV heads, head dim 128, max context 262,144 (the card calls this 256K). Our estimate has only two attention buckets, so the 18 layers that are not global attention, including the 13 convolutions, are counted with that 256-token window. Conversation memory is therefore a little higher than the 6 global and 5 sliding layers alone. At 8,192 tokens that estimate is 0.11 GB of conversation memory plus 0.80 GB of working space. LiquidAI's Q4_K_M measured 1.1 GB on 28 Oct 2026 (1,099,627,808 bytes), so the total at 8,192 tokens is 2.01 GB. Q8_0 measured 1.85 GB (1,846,238,496 bytes) and BF16 measured 3.47 GB (3,466,626,336 bytes). F16 is the same 3,466,626,336 bytes. QAD Q4_0 measured 1.05 GB (1,049,615,680 bytes). Official MLX 4-bit weights measured 0.97 GB (973,083,386 bytes). Official GGUF, MLX and ONNX builds are published. ONNX is not in the fit table. LFM Open License v1.0 allows commercial use below $10 million annual revenue. The card says that at 4-bit precision the model takes about 1 GB and fits a phone or laptop. That is Liquid AI's statement. Our total adds conversation memory and working space to the measured file. The GGUF card says the files are for local inference on CPUs and GPUs, and that llama.cpp needs an LFM3-compatible build.
Some downloads of this model (MLX) only run on Apple Silicon Macs, not on a graphics card.
Measured LFM3-1.7B on an RTX 4060 Ti 16GB yourself? Send us your llama-bench result.
Questions
- Can I run LFM3-1.7B on an RTX 4060 Ti 16GB?
- Yes. LFM3-1.7B runs on an RTX 4060 Ti 16GB, about 179 tokens per second (tok/s).
- How much memory does LFM3-1.7B need?
- About 2.0 GB at the standard quality (Q4) for a conversation of up to about 12 pages of text (8,192 tokens), by our estimate: 1.1 GB for the model file (measured), 0.1 GB to hold the conversation and 0.8 GB of working space.
- How fast is LFM3-1.7B on an RTX 4060 Ti 16GB?
- Fast: about 179 tokens per second (tok/s). Answers appear faster than you can read them. This is our estimate, not a measured test.
Speeds and memory are our estimate from the hardware specs, not a measured test. Prices are dated and may change. How we calculate