Laguna XS 2.1 (33B-A3B) on NVIDIA GeForce RTX 3060 12GB

Can the NVIDIA GeForce RTX 3060 12GB run Laguna XS 2.1 (33B-A3B)?

Yes, it runs well (offloads to RAM)

Runs well (offloads to RAM). At Q2_K it needs about 15.9 GB of 12.0 GB usable, with an estimated speed of 79.5 tok/s.

Best quant: Q2_K
Generation speed: 79.5 tok/s
Prompt processing: 2,423 tok/s
First token (1K prompt): 0.4 s
Largest safe context: —

Best app to run it on the NVIDIA GeForce RTX 3060 12GB

On Windows

LM Studio

Desktop app · runs on llama.cpp, MLX

Splits the model between GPU memory and system RAM, which this setup needs.
Point-and-click: search, download and chat in one window.

Open Laguna XS 2.1 (33B-A3B) in LM Studio

llama.cpp Splits the model between GPU memory and system RAM, which this setup needs.
Ollama Splits the model between GPU memory and system RAM, which this setup needs.

On Linux

LM Studio

Desktop app · runs on llama.cpp, MLX

Splits the model between GPU memory and system RAM, which this setup needs.
Point-and-click: search, download and chat in one window.

Open Laguna XS 2.1 (33B-A3B) in LM Studio

llama.cpp Splits the model between GPU memory and system RAM, which this setup needs.
Ollama Splits the model between GPU memory and system RAM, which this setup needs.

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download Laguna XS 2.1 (33B-A3B)

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

huggingface.co/poolside/Laguna-XS-2.1-GGUF (opens in a new tab)

ollama run hf.co/poolside/Laguna-XS-2.1-GGUF

Original weights · Hugging Face

Full-precision files from Poolside, for fine-tuning, vLLM, Transformers.

huggingface.co/poolside/Laguna-XS-2.1 (opens in a new tab)

No sign-in needed.

Links checked 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 57Good quality (B) · 57 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q2_K, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Runs welloffloads to RAM: How well it runs on the NVIDIA GeForce RTX 3060 12GB: speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	25.8 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	10.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	15.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	15.0 / 15
Match score	65.8 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every quantization on the NVIDIA GeForce RTX 3060 12GB

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	15.9 GB	12.0 GB	79.5 tok/s	Runs welloffloads to RAM	57Good quality (B) · 57 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q3_K_M`	18.9 GB	12.0 GB	54.8 tok/s	Slowheavy RAM offload	68Good quality (B) · 68 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q4_K_M`	22.9 GB	12.0 GB	38.2 tok/s	Slowheavy RAM offload	77Great quality (A) · 77 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	26.3 GB	12.0 GB	29.9 tok/s	Slowheavy RAM offload	79Great quality (A) · 79 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q6_K`	30.0 GB	12.0 GB	24.0 tok/s	Slowheavy RAM offload	81Great quality (A) · 81 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q8_0`	38.0 GB	12.0 GB	—	Won't run	82Great quality (A) · 82 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`F16`	69.4 GB	12.0 GB	—	Won't run	82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab) Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell F16 · 98.2 tok/s · Runs great
81Great quality (A) · 81 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. Apple M1 Max (64 GB) Q6_K · 72.3 tok/s · Runs great
81Great quality (A) · 81 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Max (64 GB) Q6_K · 90.1 tok/s · Runs great
79Great quality (A) · 79 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Pro (48 GB) Q5_K_M · 62.2 tok/s · Runs great
81Great quality (A) · 81 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q6_K · 179 tok/s · Runs well (tight fit)
82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Apple M2 Ultra (192 GB) F16 · 51.3 tok/s · Runs great

Quick answers

How much memory does Laguna XS 2.1 (33B-A3B) need on the RTX 3060 12GB?

At Q2_K it needs about 15.9 GB. The RTX 3060 12GB has 12.0 GB usable.

How fast is Laguna XS 2.1 (33B-A3B) on the RTX 3060 12GB?

About 79.5 tok/s at Q2_K, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Laguna XS 2.1 (33B-A3B) should I use on the RTX 3060 12GB?

Q2_K. Of the versions that fit, it is the one that runs best; when two run equally well, the check prefers the higher-rated one.

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.