Check my GPU

on

Can the NVIDIA GeForce RTX 5090 run Granite Code 20B Instruct?

71 ptsGood (B) · 71 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15

Yes, it runs well

Runs well. At Q8_0 it needs about 23.7 GB of 32.0 GB usable, with an estimated speed of 55.8 tok/s.

Best quant
Q8_0
Generation speed
55.8 tok/s
Prompt processing
3,760 tok/s
First token (1K prompt)
0.3 s
Largest safe context
8K

Download Granite Code 20B Instruct

Recommended for the NVIDIA GeForce RTX 5090: Q8_0. 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 granite-code:20b-instruct-8k-q8_0

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-20b-code-instruct-8k-GGUF (opens in a new tab)

ollama run hf.co/ibm-granite/granite-20b-code-instruct-8k-GGUF

Original weights · Hugging Face

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

huggingface.co/ibm-granite/granite-20b-code-instruct-8k (opens in a new tab)

No sign-in needed.

Links checked 1 week 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.16.2 / 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
Total71.2 / 10071 ptsGood (B) · 71 of 100 points: Model quality 16.2/45, 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 5090

Quant Memory needed Available Speed Fit Grade · points Download
Q2_K 10.4 GB 32.0 GB 180 tok/s Runs well 58 ptsGood (B) · 58 of 100 points: Model quality 11.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.5/15
Q3_K_M 12.3 GB 32.0 GB 142 tok/s Runs well 62 ptsGood (B) · 62 of 100 points: Model quality 13.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.8/15
Q4_K_M 14.7 GB 32.0 GB 110 tok/s Runs well 65 ptsGood (B) · 65 of 100 points: Model quality 15.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.6/15 GGUF (opens in a new tab)
Q5_K_M 16.7 GB 32.0 GB 90.5 tok/s Runs well 67 ptsGood (B) · 67 of 100 points: Model quality 15.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.0/15
Q6_K 18.9 GB 32.0 GB 76.0 tok/s Runs well 69 ptsGood (B) · 69 of 100 points: Model quality 16.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.6/15
Q8_0 23.7 GB 32.0 GB 55.8 tok/s Runs well 71 ptsGood (B) · 71 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15
F16 42.6 GB 32.0 GB 3.3 tok/s Runs with offload 45 ptsUsable (C) · 45 of 100 points: Model quality 16.2/45, Memory fit 10.0/25, Speed 4.3/15, Memory use 15.0/15 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.