Check my GPU

LLMs ·

Granite 4.1 8B

Parameters
8.8B
Architecture
Dense
Max context
128K tokens
License
apache-2.0
Released
2026-04

How to run it

Quickest · Ollama

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

ollama run granite4.1:8b

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.

huggingface.co/ibm-granite/granite-4.1-8b-GGUF (opens in a new tab)

ollama run hf.co/ibm-granite/granite-4.1-8b-GGUF

Original weights · Hugging Face

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

huggingface.co/ibm-granite/granite-4.1-8b (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-4.1-language-models (opens in a new tab)

git clone https://github.com/ibm-granite/granite-4.1-language-models

Links checked 5 days ago against Hugging Face, Ollama and GitHub.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps.

Quantization Quality Weights Total at 8K context Total at 32K context Download
Q2_K Low 3.5 GB 5.5 GB 9.5 GB GGUF (opens in a new tab)
Q3_K_M Low 4.3 GB 6.2 GB 10.3 GB GGUF (opens in a new tab)
Q4_K_M Good 5.4 GB 7.3 GB 11.3 GB GGUF (opens in a new tab)
Q5_K_M High 6.2 GB 8.2 GB 12.2 GB GGUF (opens in a new tab)
Q6_K High 7.2 GB 9.1 GB 13.2 GB GGUF (opens in a new tab)
Q8_0 Very high 9.3 GB 11.3 GB 15.3 GB GGUF (opens in a new tab)
F16 Full 17.6 GB 19.5 GB 23.5 GB GGUF (opens in a new tab) Original weights (opens in a new tab)

Best hardware for Granite 4.1 8B

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc A380 (launch price $139) at Q2_K.

Grade · points Hardware Quant Memory Speed Fit
82 ptsGreat (A) · 82 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5090 F16 21.1 GB / 32.0 GB 58.7 tok/s Runs well
82 ptsGreat (A) · 82 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4070 Ti SUPER Q8_0 12.1 GB / 16.0 GB 47.8 tok/s Runs well
82 ptsGreat (A) · 82 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4080 SUPER Q8_0 12.1 GB / 16.0 GB 52.3 tok/s Runs well
82 ptsGreat (A) · 82 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5070 Ti Q8_0 12.1 GB / 16.0 GB 63.7 tok/s Runs well
82 ptsGreat (A) · 82 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5080 Q8_0 12.1 GB / 16.0 GB 68.2 tok/s Runs well
81 ptsGreat (A) · 81 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 14.8/15, Memory use 15.0/15 AMD Radeon RX 9070 XT Q8_0 12.1 GB / 16.0 GB 39.2 tok/s Runs well
81 ptsGreat (A) · 81 of 100 points: Model quality 26.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4070 SUPER Q6_K 9.7 GB / 12.0 GB 48.8 tok/s Runs well
81 ptsGreat (A) · 81 of 100 points: Model quality 26.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 Intel Arc B580 Q5_K_M 8.8 GB / 12.0 GB 40.2 tok/s Runs well
81 ptsGreat (A) · 81 of 100 points: Model quality 26.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 3060 12GB Q5_K_M 8.8 GB / 12.0 GB 41.5 tok/s Runs well
81 ptsGreat (A) · 81 of 100 points: Model quality 26.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.4/15 NVIDIA GeForce RTX 5060 Ti 16GB Q6_K 9.9 GB / 16.0 GB 43.4 tok/s Runs well

Check it on your own hardware

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.