Check my GPU

on

Can the NVIDIA GeForce RTX 4070 SUPER run Granite 4.0 Micro (3B)?

73 ptsGreat (A) · 73 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15

Yes, it runs well

Runs well. At F16 it needs about 8.7 GB of 12.0 GB usable, with an estimated speed of 42.7 tok/s.

Best quant
F16
Generation speed
42.7 tok/s
Prompt processing
7,518 tok/s
First token (1K prompt)
0.3 s
Largest safe context
47K

Download Granite 4.0 Micro (3B)

Recommended for the NVIDIA GeForce RTX 4070 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 granite4:micro

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-4.0-micro-GGUF (opens in a new tab)

ollama run hf.co/ibm-granite/granite-4.0-micro-GGUF:BF16

Original weights · Hugging Face

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

huggingface.co/ibm-granite/granite-4.0-micro (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-4.0-language-models (opens in a new tab)

git clone https://github.com/ibm-granite/granite-4.0-language-models

IBM’s official Granite 4.0 repo.

Links checked 1 week ago against Hugging Face, Ollama and GitHub.

How the A 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.18.0 / 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.15.0 / 15
Total73.0 / 10073 ptsGreat (A) · 73 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15

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

Every quantization on the NVIDIA GeForce RTX 4070 SUPER

Quant Memory needed Available Speed Fit Grade · points Download
Q2_K 3.2 GB 12.0 GB 299 tok/s Runs well 58 ptsGood (B) · 58 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.2/15 GGUF (opens in a new tab)
Q3_K_M 3.5 GB 12.0 GB 235 tok/s Runs well 61 ptsGood (B) · 61 of 100 points: Model quality 15.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.8/15 GGUF (opens in a new tab)
Q4_K_M 3.9 GB 12.0 GB 182 tok/s Runs well 64 ptsGood (B) · 64 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.6/15 GGUF (opens in a new tab)
Q5_K_M 4.3 GB 12.0 GB 150 tok/s Runs well 65 ptsGood (B) · 65 of 100 points: Model quality 17.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.2/15 GGUF (opens in a new tab)
Q6_K 4.7 GB 12.0 GB 126 tok/s Runs well 66 ptsGood (B) · 66 of 100 points: Model quality 17.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.0/15 GGUF (opens in a new tab)
Q8_0 5.5 GB 12.0 GB 92.6 tok/s Runs well 68 ptsGood (B) · 68 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.5/15 GGUF (opens in a new tab)
F16 8.7 GB 12.0 GB 42.7 tok/s Runs well 73 ptsGreat (A) · 73 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 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

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.