Can Granite Code 20B run on AMD Instinct MI60 32GB?

YES — Runs Great

A82Great

Estimated from fit model

Granite Code 20B needs ~19.5 GB VRAM. AMD Instinct MI60 32GB has 32.0 GB. With Q4_K_M quantization, expect ~44 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: HighStack: StandardBottleneck: Balanced

Operating mode

Choose the run profile you care about

Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.

Current mode

Balanced

Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 19.5 GB, 44.4 tok/s, Runs well

19.5 GB required32.0 GB available

61% VRAM used

Fit status

Runs well

Decode

44.4 tok/s

TTFT

4359 ms

Safe context

Memory

19.5 GB / 32.0 GB

Memory breakdown

Weights12.2 GB

KV Cache3.2 GB

Runtime0.9 GB

Headroom3.2 GB

See how fast it feels

See how fast it feelsGranite Code 20B on AMD Instinct MI60 32GB
1st promptCold start — includes initialization
>Write a Python function to sort a list
Here's a Python function that sorts a list using quicksort:

def quicksort(arr):
    if len(arr) <= 1:
        return arr
    pivot = arr[len(arr) // 2]
    left   = [x for x in arr if x < pivot]
    middle = [x for x in arr if x == pivot]
    right  = [x for x in arr if x > pivot]
    return quicksort(left) + middle + quicksort(right)

# Example usage
numbers = [3, 6, 8, 10, 1, 2, 1]
print(quicksort(numbers))  # [1, 1, 2, 3, 6, 8, 10]

The algorithm picks a pivot, partitions the list into smaller, equal, and larger elements, then recursively sorts each partition and concatenates the results.
2nd promptWarm — model ready, no init overhead
>Now add type hints and a docstring
def quicksort(arr: list[int]) -> list[int]:
    """Sort a list using the quicksort algorithm.

    Args:
        arr: List of integers to sort.

    Returns:
        A new sorted list.
    """
    if len(arr) <= 1:
        return arr
    pivot = arr[len(arr) // 2]
    left   = [x for x in arr if x < pivot]
    middle = [x for x in arr if x == pivot]
    right  = [x for x in arr if x > pivot]
    return quicksort(left) + middle + quicksort(right)

Added type hints for the input and return type, plus a Google-style docstring.
Estimated: 44.4 tok/s decode · 4.4s TTFT (warm) · 111 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

No major red flags

This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.

Best improvement path

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	A	Runs well	44.4 tok/s	2377 ms	8K
Coding	A	Runs well	44.4 tok/s	4359 ms	8K
Agentic Coding	A	Runs well	44.4 tok/s	6340 ms	8K
Reasoning	A	Runs well	44.4 tok/s	5151 ms	8K
RAG	A	Runs well	44.4 tok/s	7925 ms	8K

Inference speed

Granite Code 20B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Granite Code 20B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~106 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.

GPU / Mac	Memory	Quant	Speed (tok/s)	Fits?
RTX 5090 32GB	32 GB	Q4_K_M	106.3	Fits
RTX 4090 24GB	24 GB	Q4_K_M	67.8	Fits
RX 7900 XTX 24GB	24 GB	Q4_K_M	61.2	Fits
RTX 3090 24GB	24 GB	Q4_K_M	58.0	Fits
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	49.3	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	41.1	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	39.0	Fits
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	38.4	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	38.4	Fits
RTX 4080 Super 16GB	16 GB	Q4_K_M	31.0	Heavy offload
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	24.2	Fits
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	21.2	Fits
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	19.5	Fits
RTX 4070 12GB	12 GB	Q4_K_M	11.0	Too big
RTX 3060 12GB	12 GB	Q4_K_M	6.9	Too big
RTX 4060 8GB	8 GB	Q4_K_M	2.6	Too big

Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.

Quantization options

How Granite Code 20B (20B params) fits at each quantization level on AMD Instinct MI60 32GB (32.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	7.8 GB	Low	A75
Q3_K_S	3	9.8 GB	Low	A75
NVFP4	4	11.2 GB	Medium	A76
Q4_K_M	4	12.2 GB	Medium	A77
Q5_K_M	5	14.4 GB	High	A78
Q6_K	6	16.4 GB	High	A79
Q8_0Best for your GPU	8	21.4 GB	Very High	A79
F16	16	41.0 GB	Maximum	F0

Get started

Copy-paste commands to run Granite Code 20B on your machine.

Run

ollama run granite-code:20b

Your hardware

More models your AMD Instinct MI60 32GB can run

Model	Params	Grade	Decode
Qwen3-Coder 30B A3B Instruct	30.5B	S	75.9 tok/s
Qwen 3.5 27B	27B	S	32.9 tok/s
Qwen 3.6 27B	27B	S	20.5 tok/s
Qwen 3.6 35B A3B	35B	S	63.8 tok/s
Qwen3-VL 30B A3B Instruct	30B	S	78.5 tok/s

Frequently asked questions

Can AMD Instinct MI60 32GB run Granite Code 20B?

Yes, AMD Instinct MI60 32GB can run Granite Code 20B with a A grade (Runs well). Expected decode speed: 44.4 tok/s.

How much VRAM does Granite Code 20B need?

Granite Code 20B (20B parameters) requires approximately 19.5 GB of memory with Q4_K_M quantization.

What is the best quantization for Granite Code 20B?

The recommended quantization for Granite Code 20B is Q4_K_M, which balances quality and memory efficiency.

What speed will Granite Code 20B run at on AMD Instinct MI60 32GB?

On AMD Instinct MI60 32GB, Granite Code 20B achieves approximately 44.4 tokens per second decode speed with a time-to-first-token of 4359ms using Q4_K_M quantization.

Can AMD Instinct MI60 32GB run Granite Code 20B for coding?

For coding workloads, Granite Code 20B on AMD Instinct MI60 32GB receives a A grade with 44.4 tok/s and 8K context.

What context window can Granite Code 20B use on AMD Instinct MI60 32GB?

On AMD Instinct MI60 32GB, Granite Code 20B can safely use up to 8K tokens of context. The model's official context limit is 8K, but available memory constrains the safe maximum.

See all results for AMD Instinct MI60 32GB See all hardware for Granite Code 20B

Embed this result▼

Paste this snippet into any page to show a live fit card.

<iframe src="https://willitrunai.com/embed/granite-code-20b-on-instinct-mi60-32gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview:

Workload

Grade

Fit

Decode

TTFT

Context

Chat

Runs well

44.4 tok/s

2377 ms

Coding

Runs well

44.4 tok/s

4359 ms

Agentic Coding

Runs well

44.4 tok/s

6340 ms

Reasoning

Runs well

44.4 tok/s

5151 ms

RAG

Runs well

44.4 tok/s

7925 ms

Granite Code 20B inference speed — tokens per second by GPU & Mac

GPU / Mac

Memory

Quant

Speed (tok/s)

Fits?

RTX 5090 32GB

32 GB

Q4_K_M

106.3

Fits

RTX 4090 24GB

24 GB

Q4_K_M

67.8

Fits

RX 7900 XTX 24GB

24 GB

Q4_K_M

61.2

Fits

RTX 3090 24GB

24 GB

Q4_K_M

58.0

Fits

Mac Studio M3 Ultra 256GB

256 GB

Q4_K_M

49.3

Fits

Mac Studio M2 Ultra 128GB

128 GB

Q4_K_M

41.1

Fits

Mac Studio M1 Ultra 128GB

128 GB

Q4_K_M

39.0

Fits

MacBook Pro M4 Max 128GB

128 GB

Q4_K_M

38.4

Fits

MacBook Pro M4 Max 64GB

64 GB

Q4_K_M

38.4

Fits

RTX 4080 Super 16GB

16 GB

Q4_K_M

31.0

Heavy offload

MacBook Pro M4 Pro 48GB

48 GB

Q4_K_M

24.2

Fits

MacBook Pro M3 Max 64GB

64 GB

Q4_K_M

21.2

Fits

MacBook Pro M1 Max 64GB

64 GB

Q4_K_M

19.5

Fits

RTX 4070 12GB

12 GB

Q4_K_M

11.0

Too big

RTX 3060 12GB

12 GB

Q4_K_M

6.9

Too big

RTX 4060 8GB

8 GB

Q4_K_M

2.6

Too big

Quantization options

How Granite Code 20B (20B params) fits at each quantization level on AMD Instinct MI60 32GB (32.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	7.8 GB	Low	A75
Q3_K_S	3	9.8 GB	Low	A75
NVFP4	4	11.2 GB	Medium	A76
Q4_K_M	4	12.2 GB	Medium	A77
Q5_K_M	5	14.4 GB	High	A78
Q6_K	6	16.4 GB	High	A79
Q8_0Best for your GPU	8	21.4 GB	Very High	A79
F16	16	41.0 GB	Maximum	F0

Model

Params

Grade

Decode

Capabilities

Qwen3-Coder 30B A3B Instruct

30.5B

75.9 tok/s

Qwen 3.5 27B

27B

32.9 tok/s

Qwen 3.6 27B

27B

20.5 tok/s

Qwen 3.6 35B A3B

35B

63.8 tok/s

Qwen3-VL 30B A3B Instruct

30B

78.5 tok/s

Frequently asked questions

Can AMD Instinct MI60 32GB run Granite Code 20B?

Yes, AMD Instinct MI60 32GB can run Granite Code 20B with a A grade (Runs well). Expected decode speed: 44.4 tok/s.

How much VRAM does Granite Code 20B need?

Granite Code 20B (20B parameters) requires approximately 19.5 GB of memory with Q4_K_M quantization.

What is the best quantization for Granite Code 20B?

The recommended quantization for Granite Code 20B is Q4_K_M, which balances quality and memory efficiency.

What speed will Granite Code 20B run at on AMD Instinct MI60 32GB?

On AMD Instinct MI60 32GB, Granite Code 20B achieves approximately 44.4 tokens per second decode speed with a time-to-first-token of 4359ms using Q4_K_M quantization.

Can AMD Instinct MI60 32GB run Granite Code 20B for coding?

For coding workloads, Granite Code 20B on AMD Instinct MI60 32GB receives a A grade with 44.4 tok/s and 8K context.

What context window can Granite Code 20B use on AMD Instinct MI60 32GB?

On AMD Instinct MI60 32GB, Granite Code 20B can safely use up to 8K tokens of context. The model's official context limit is 8K, but available memory constrains the safe maximum.