Granite Code 20B Instruct on AMD Radeon AI PRO R9600D

Can the AMD Radeon AI PRO R9600D run Granite Code 20B Instruct?

Yes, it runs great

Runs great. At Q4_K_M it needs about 14.7 GB of 32.0 GB usable, with an estimated speed of 33.7 tok/s.

Best quant: Q4_K_M
Generation speed: 33.7 tok/s
Prompt processing: 1,532 tok/s
First token (1K prompt): 0.7 s
Largest safe context: 8K

Best app to run it on the AMD Radeon AI PRO R9600D

On Windows

Lemonade

Desktop app · runs on llama.cpp, ONNX Runtime GenAI (Ryzen AI NPU)

AMD’s own app: llama.cpp tuned for Radeon on Vulkan and ROCm.

lemonade pull ibm-granite/granite-20b-code-instruct-8k-GGUF:Q4_K_M

LM Studio Point-and-click: search, download and chat in one window.
Ollama One command with Ollama’s own build of this model.

On Linux

Lemonade

Desktop app · runs on llama.cpp, ONNX Runtime GenAI (Ryzen AI NPU)

AMD’s own app: llama.cpp tuned for Radeon on Vulkan and ROCm.

lemonade pull ibm-granite/granite-20b-code-instruct-8k-GGUF:Q4_K_M

LM Studio Point-and-click: search, download and chat in one window.
Ollama One command with Ollama’s own build of this model.

Want an agent? Granite Code 20B Instruct supports tool use, so you can pair a llama.cpp or MLX LM server with one of these. Apps that run on this computer come first.

Coding agents

Personal assistants

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 Granite Code 20B Instruct

Recommended for the AMD Radeon AI PRO R9600D: Q4_K_M. 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.

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

ollama run granite-code:20b-instruct-8k-q4_K_M

Quantized files · GGUF

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

Download the Q4_K_M file (opens in a new tab)

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:Q4_K_M

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 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q4_K_M, 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 great: How well it runs on the AMD Radeon AI PRO R9600D: 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.	15.4 / 45
Memory fitFull marks when everything sits in GPU 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.	13.8 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	10.6 / 15
Match score	64.7 / 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 AMD Radeon AI PRO R9600D

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	10.4 GB	32.0 GB	55.4 tok/s	Runs great	25Basic quality (D) · 25 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.
`Q3_K_M`	12.3 GB	32.0 GB	43.6 tok/s	Runs great	30Basic quality (D) · 30 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.
`Q4_K_M`	14.7 GB	32.0 GB	33.7 tok/s	Runs great	34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	16.7 GB	32.0 GB	27.8 tok/s	Runs well	34Basic quality (D) · 34 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.
`Q6_K`	18.9 GB	32.0 GB	23.4 tok/s	Runs well	35Basic quality (D) · 35 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.
`Q8_0`	23.7 GB	32.0 GB	17.2 tok/s	Runs well	36Basic quality (D) · 36 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.
`F16`	42.6 GB	32.0 GB	2.7 tok/s	Very slowoffloads to RAM	36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking.	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

36Basic quality (D) · 36 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q8_0 · 55.8 tok/s · Runs great
35Basic quality (D) · 35 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Q6_K · 42.8 tok/s · Runs great
35Basic quality (D) · 35 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3090 Q6_K · 39.7 tok/s · Runs great
34Basic quality (D) · 34 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q5_K_M · 41.8 tok/s · Runs great
34Basic quality (D) · 34 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5070 Ti Q5_K_M · 45.3 tok/s · Runs well (tight fit)
34Basic quality (D) · 34 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5080 Q5_K_M · 48.5 tok/s · Runs well (tight fit)

Quick answers

How much memory does Granite Code 20B Instruct need on the AI PRO R9600D 32GB?

At Q4_K_M it needs about 14.7 GB. The AI PRO R9600D 32GB has 32.0 GB usable.

How fast is Granite Code 20B Instruct on the AI PRO R9600D 32GB?

About 33.7 tok/s at Q4_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Granite Code 20B Instruct should I use on the AI PRO R9600D 32GB?

Q4_K_M. 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.