Can GPT-OSS 20B run on Radeon Pro W7900 48GB?

YES — Runs Great

S90Excellent

Estimated from fit model

GPT-OSS 20B needs ~21.0 GB VRAM. Radeon Pro W7900 48GB has 48.0 GB. With Q4_K_M quantization, expect ~98 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) — 21.0 GB, 97.9 tok/s, Runs well

21.0 GB required48.0 GB available

44% VRAM used

Fit status

Runs well

Decode

97.9 tok/s

TTFT

1978 ms

Safe context

128K

Memory

21.0 GB / 48.0 GB

Memory breakdown

Weights12.8 GB

KV Cache2.4 GB

Runtime0.9 GB

Headroom4.8 GB

See how fast it feels

See how fast it feelsGPT-OSS 20B on Radeon Pro W7900 48GB
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: 97.9 tok/s decode · 2.0s TTFT (warm) · 245 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	S	Runs well	97.9 tok/s	1079 ms	128K
Coding	S	Runs well	97.9 tok/s	1978 ms	128K
Agentic Coding	S	Runs well	97.9 tok/s	2878 ms	128K
Reasoning	S	Runs well	97.9 tok/s	2338 ms	128K
RAG	S	Runs well	97.9 tok/s	3597 ms	128K

Inference speed

GPT-OSS 20B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for GPT-OSS 20B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~231 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	230.5	Fits
RTX 4090 24GB	24 GB	Q4_K_M	147.1	Fits
RX 7900 XTX 24GB	24 GB	Q4_K_M	132.7	Fits
RTX 3090 24GB	24 GB	Q4_K_M	125.8	Fits
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	106.9	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	89.1	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	84.5	Fits
RTX 4080 Super 16GB	16 GB	Q4_K_M	68.2	Heavy offload
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	66.0	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	66.0	Fits
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	46.1	Fits
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	42.2	Fits
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	40.4	Fits
RTX 4070 12GB	12 GB	Q4_K_M	24.2	Too big
RTX 3060 12GB	12 GB	Q4_K_M	15.2	Too big
RTX 4060 8GB	8 GB	Q4_K_M	5.7	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 GPT-OSS 20B (21B params) fits at each quantization level on Radeon Pro W7900 48GB (48.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.2 GB	Low	A81
Q3_K_S	3	10.3 GB	Low	A82
NVFP4	4	11.8 GB	Medium	A82
Q4_K_M	4	12.8 GB	Medium	A82
Q5_K_M	5	15.1 GB	High	A83
Q6_K	6	17.2 GB	High	A84
Q8_0Best for your GPU	8	22.5 GB	Very High	S85
F16	16	43.1 GB	Maximum	F0

Get started

Copy-paste commands to run GPT-OSS 20B on your machine.

Run

ollama run gpt-oss

Your hardware

More models your Radeon Pro W7900 48GB can run

Model	Params	Grade	Decode
Qwen3-Coder 30B A3B Instruct	30.5B	S	77.1 tok/s
Qwen 3.5 27B	27B	S	33.4 tok/s
Qwen 3.6 27B	27B	S	23.9 tok/s
Qwen 3.6 35B A3B	35B	S	64.8 tok/s
Qwen3-VL 30B A3B Instruct	30B	S	79.7 tok/s

Frequently asked questions

Can Radeon Pro W7900 48GB run GPT-OSS 20B?

Yes, Radeon Pro W7900 48GB can run GPT-OSS 20B with a S grade (Runs well). Expected decode speed: 97.9 tok/s.

How much VRAM does GPT-OSS 20B need?

GPT-OSS 20B (21B parameters) requires approximately 21.0 GB of memory with Q4_K_M quantization.

What is the best quantization for GPT-OSS 20B?

The recommended quantization for GPT-OSS 20B is Q4_K_M, which balances quality and memory efficiency.

What speed will GPT-OSS 20B run at on Radeon Pro W7900 48GB?

On Radeon Pro W7900 48GB, GPT-OSS 20B achieves approximately 97.9 tokens per second decode speed with a time-to-first-token of 1978ms using Q4_K_M quantization.

Can Radeon Pro W7900 48GB run GPT-OSS 20B for coding?

For coding workloads, GPT-OSS 20B on Radeon Pro W7900 48GB receives a S grade with 97.9 tok/s and 128K context.

What context window can GPT-OSS 20B use on Radeon Pro W7900 48GB?

On Radeon Pro W7900 48GB, GPT-OSS 20B can safely use up to 128K tokens of context. The model's official context limit is 128K, but available memory constrains the safe maximum.

See all results for Radeon Pro W7900 48GB See all hardware for GPT-OSS 20B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/gpt-oss-20b-on-radeon-pro-w7900-48gb" 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

97.9 tok/s

1079 ms

128K

Coding

Runs well

97.9 tok/s

1978 ms

128K

Agentic Coding

Runs well

97.9 tok/s

2878 ms

128K

Reasoning

Runs well

97.9 tok/s

2338 ms

128K

RAG

Runs well

97.9 tok/s

3597 ms

128K

GPT-OSS 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

230.5

Fits

RTX 4090 24GB

24 GB

Q4_K_M

147.1

Fits

RX 7900 XTX 24GB

24 GB

Q4_K_M

132.7

Fits

RTX 3090 24GB

24 GB

Q4_K_M

125.8

Fits

Mac Studio M3 Ultra 256GB

256 GB

Q4_K_M

106.9

Fits

Mac Studio M2 Ultra 128GB

128 GB

Q4_K_M

89.1

Fits

Mac Studio M1 Ultra 128GB

128 GB

Q4_K_M

84.5

Fits

RTX 4080 Super 16GB

16 GB

Q4_K_M

68.2

Heavy offload

MacBook Pro M4 Max 128GB

128 GB

Q4_K_M

66.0

Fits

MacBook Pro M4 Max 64GB

64 GB

Q4_K_M

66.0

Fits

MacBook Pro M3 Max 64GB

64 GB

Q4_K_M

46.1

Fits

MacBook Pro M1 Max 64GB

64 GB

Q4_K_M

42.2

Fits

MacBook Pro M4 Pro 48GB

48 GB

Q4_K_M

40.4

Fits

RTX 4070 12GB

12 GB

Q4_K_M

24.2

Too big

RTX 3060 12GB

12 GB

Q4_K_M

15.2

Too big

RTX 4060 8GB

8 GB

Q4_K_M

5.7

Too big

Quantization options

How GPT-OSS 20B (21B params) fits at each quantization level on Radeon Pro W7900 48GB (48.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.2 GB	Low	A81
Q3_K_S	3	10.3 GB	Low	A82
NVFP4	4	11.8 GB	Medium	A82
Q4_K_M	4	12.8 GB	Medium	A82
Q5_K_M	5	15.1 GB	High	A83
Q6_K	6	17.2 GB	High	A84
Q8_0Best for your GPU	8	22.5 GB	Very High	S85
F16	16	43.1 GB	Maximum	F0

Model

Params

Grade

Decode

Capabilities

Qwen3-Coder 30B A3B Instruct

30.5B

77.1 tok/s

Qwen 3.5 27B

27B

33.4 tok/s

Qwen 3.6 27B

27B

23.9 tok/s

Qwen 3.6 35B A3B

35B

64.8 tok/s

Qwen3-VL 30B A3B Instruct

30B

79.7 tok/s

Frequently asked questions

Can Radeon Pro W7900 48GB run GPT-OSS 20B?

Yes, Radeon Pro W7900 48GB can run GPT-OSS 20B with a S grade (Runs well). Expected decode speed: 97.9 tok/s.

How much VRAM does GPT-OSS 20B need?

GPT-OSS 20B (21B parameters) requires approximately 21.0 GB of memory with Q4_K_M quantization.

What is the best quantization for GPT-OSS 20B?

The recommended quantization for GPT-OSS 20B is Q4_K_M, which balances quality and memory efficiency.

What speed will GPT-OSS 20B run at on Radeon Pro W7900 48GB?

On Radeon Pro W7900 48GB, GPT-OSS 20B achieves approximately 97.9 tokens per second decode speed with a time-to-first-token of 1978ms using Q4_K_M quantization.

Can Radeon Pro W7900 48GB run GPT-OSS 20B for coding?

For coding workloads, GPT-OSS 20B on Radeon Pro W7900 48GB receives a S grade with 97.9 tok/s and 128K context.

What context window can GPT-OSS 20B use on Radeon Pro W7900 48GB?

On Radeon Pro W7900 48GB, GPT-OSS 20B can safely use up to 128K tokens of context. The model's official context limit is 128K, but available memory constrains the safe maximum.