Granite 3.3 2B on NVIDIA GeForce RTX 4080 SUPER

Can the NVIDIA GeForce RTX 4080 SUPER run Granite 3.3 2B?

63 pts

Yes, it runs well

Runs well. At F16 it needs about 7.1 GB of 16.0 GB usable, with an estimated speed of 83.8 tok/s.

Best quant: F16
Generation speed: 83.8 tok/s
Prompt processing: 14,855 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 113K

Download Granite 3.3 2B

Recommended for the NVIDIA GeForce RTX 4080 SUPER: F16. Every other quantization has its own download link in the table below.

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

ollama run granite3.3:2b

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

Quantized files · GGUF

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

Download the F16 file (opens in a new tab)

huggingface.co/ibm-granite/granite-3.3-2b-instruct-GGUF (opens in a new tab)

ollama run hf.co/ibm-granite/granite-3.3-2b-instruct-GGUF:F16

Original weights · Hugging Face

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

huggingface.co/ibm-granite/granite-3.3-2b-instruct (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from IBM. The weights themselves download from Hugging Face.

github.com/ibm-granite/granite-3.3-language-models (opens in a new tab)

git clone https://github.com/ibm-granite/granite-3.3-language-models

Links checked 7 days ago against Hugging Face, Ollama and GitHub.

How the B grade is scored

Every result gets up to 100 points from four parts. The points decide the letter grade.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	13.5 / 45
Memory fitFull marks when everything sits in GPU or unified memory; fewer when part spills to system RAM.	25.0 / 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.	10.3 / 15
Total	63.8 / 100	63 ptsGood (B) · 63 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.3/15

Grade scale: S 85+ · A 72+ · B 58+ · C 42+ · D 25+ · F under 25 points.

Every quantization on the NVIDIA GeForce RTX 4080 SUPER

Quant	Memory needed	Available	Speed	Fit	Grade · points	Download
`Q2_K`	3.1 GB	16.0 GB	586 tok/s	Runs well	53 ptsUsable (C) · 53 of 100 points: Model quality 9.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.4/15	GGUF (opens in a new tab)
`Q3_K_M`	3.3 GB	16.0 GB	462 tok/s	Runs well	56 ptsUsable (C) · 56 of 100 points: Model quality 11.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.8/15	GGUF (opens in a new tab)
`Q4_K_M`	3.6 GB	16.0 GB	357 tok/s	Runs well	58 ptsGood (B) · 58 of 100 points: Model quality 12.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.2/15	GGUF (opens in a new tab)
`Q5_K_M`	3.9 GB	16.0 GB	295 tok/s	Runs well	58 ptsGood (B) · 58 of 100 points: Model quality 13.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.6/15	GGUF (opens in a new tab)
`Q6_K`	4.1 GB	16.0 GB	248 tok/s	Runs well	59 ptsGood (B) · 59 of 100 points: Model quality 13.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.0/15	GGUF (opens in a new tab)
`Q8_0`	4.8 GB	16.0 GB	182 tok/s	Runs well	60 ptsGood (B) · 60 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.9/15	GGUF (opens in a new tab)
`F16`	7.1 GB	16.0 GB	83.8 tok/s	Runs well	63 ptsGood (B) · 63 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.3/15	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

66 ptsGood (B) · 66 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.3/15 NVIDIA GeForce RTX 3060 12GB F16 · 41.0 tok/s
66 ptsGood (B) · 66 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.3/15 NVIDIA GeForce RTX 4070 SUPER F16 · 57.4 tok/s
66 ptsGood (B) · 66 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.6/15 NVIDIA GeForce RTX 4060 Q8_0 · 67.2 tok/s
63 ptsGood (B) · 63 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.3/15 AMD Radeon RX 9070 XT F16 · 62.7 tok/s
63 ptsGood (B) · 63 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.3/15 NVIDIA GeForce RTX 4070 Ti SUPER F16 · 76.5 tok/s

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.