Can Command A 111B run on Radeon PRO W7900 DS 48GB?

YES — With Q2_K

A76Great

Estimated from fit model

Command A 111B needs ~52.9 GB VRAM. Radeon PRO W7900 DS 48GB has 48.0 GB. With Q2_K quantization, expect ~7 tok/s.

Runtime: llama.cppCapacity: OffloadBandwidth: HighStack: StandardBottleneck: Host offload

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.

Command A 111B at Q4_K_M needs 77.3 GB — too much for Radeon PRO W7900 DS 48GB (48.0 GB). Runs at Q2_K (52.9 GB) with low quality.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 77.3 GB, exceeds 48.0 GB available

77.3 GB required48.0 GB available

161% VRAM needed

29.3 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

2.3 tok/s

TTFT

85672 ms

Safe context

Memory

77.3 GB / 48.0 GB

Offload

40%

Memory breakdown

Weights67.7 GB

KV Cache3.9 GB

Runtime0.9 GB

Headroom4.8 GB

See how fast it feels

With memory offload — actual speed may be lower

See how fast it feelsCommand A 111B on Radeon PRO W7900 DS 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: 2.3 tok/s decode · 85.7s TTFT (warm) · 6 tok/s prefill

What limits this setup

It fits through host-memory offload, and offload is the main reason performance drops.

CPU or host-memory offload is active

About 10% of the working set spills out of accelerator memory, which usually hurts latency and sustained decode throughput.

Very little memory headroom

You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.

Best improvement path

Remove offload with more accelerator memory

Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.

Buy headroom, not only minimum fit

A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

Increase host RAM if you keep offloading

This setup may need roughly 4.0 GB of extra host RAM just for the offloaded portion, before OS and other tools.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	F	Too heavy	2.4 tok/s	44280 ms	4K
Coding	F	Too heavy	2.3 tok/s	85672 ms	4K
Agentic Coding	F	Too heavy	2.0 tok/s	138237 ms	4K
Reasoning	F	Too heavy	2.3 tok/s	101249 ms	4K
RAG	F	Too heavy	2.0 tok/s	172796 ms	4K

Inference speed

Command A 111B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Command A 111B at Q4_K_M across popular GPUs and Apple Silicon, including multi-GPU rigs, using the fastest local runtime per device. Fastest is MacBook Pro M4 Max 128GB at ~10 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?
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	9.7	Tight
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	9.0	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	7.5	Tight
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	7.1	Tight
2× RX 7900 XTX 24GB	48 GB	Q4_K_M	5.2	Too big
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	4.8	Too big
2× RTX 4090 24GB	48 GB	Q4_K_M	3.7	Too big
2× RTX 3090 24GB	48 GB	Q4_K_M	3.1	Too big
4× RTX 3060 12GB	48 GB	Q4_K_M	2.8	Too big
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	2.7	Too big
RTX 5090 32GB	32 GB	Q4_K_M	2.0	Too big
RTX 4090 24GB	24 GB	Q4_K_M	2.0	Too big
RTX 4080 Super 16GB	16 GB	Q4_K_M	2.0	Too big
RTX 3090 24GB	24 GB	Q4_K_M	2.0	Too big
RTX 4070 12GB	12 GB	Q4_K_M	2.0	Too big
RTX 3060 12GB	12 GB	Q4_K_M	2.0	Too big
RTX 4060 8GB	8 GB	Q4_K_M	2.0	Too big
RX 7900 XTX 24GB	24 GB	Q4_K_M	2.0	Too big
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	2.0	Too big
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	2.0	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 Command A 111B (111B params) fits at each quantization level on Radeon PRO W7900 DS 48GB (48.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	43.3 GB	Low	F0
Q3_K_S	3	54.4 GB	Low	F0
NVFP4	4	62.2 GB	Medium	F0
Q4_K_M	4	67.7 GB	Medium	F0
Q5_K_M	5	79.9 GB	High	F0
Q6_K	6	91.0 GB	High	F0
Q8_0	8	118.8 GB	Very High	F0
F16	16	227.6 GB	Maximum	F0

Get started

Copy-paste commands to run Command A 111B on your machine.

Run

ollama run command-a

Upgrade-Optionen

Hardware, die Command A 111B gut ausführt

AMD Instinct MI350X 288GBGünstige Wahl

288 GB VRAM (+240)8000 GB/s (+7136)

Makes the model fit on the accelerator instead of staying completely out of reach.94.2 tok/s Dekodierung

Makes the model fit on the accelerator instead of staying completely out of reach.

Removes host-memory offload, which is usually the single biggest latency and throughput win.

ca. $8,000 MSRP

AMD Instinct MI300A 128GBBestes Preis-Leistungs-Verhältnis

128 GB VRAM (+80)5300 GB/s (+4436)

Makes the model fit on the accelerator instead of staying completely out of reach.59.8 tok/s Dekodierung

Makes the model fit on the accelerator instead of staying completely out of reach.

Removes host-memory offload, which is usually the single biggest latency and throughput win.

ca. $12,000 MSRP

AMD Instinct MI250X 128GBAMD-Upgrade

128 GB VRAM (+80)3200 GB/s (+2336)

Makes the model fit on the accelerator instead of staying completely out of reach.40.2 tok/s Dekodierung

Makes the model fit on the accelerator instead of staying completely out of reach.

Removes host-memory offload, which is usually the single biggest latency and throughput win.

ca. $15,000 MSRP

Frequently asked questions

Can Radeon PRO W7900 DS 48GB run Command A 111B?

Yes, Radeon PRO W7900 DS 48GB can run Command A 111B at Q2_K quantization (Very compromised (needs ~4 GB host RAM)). The recommended Q4_K_M requires 77.3 GB which exceeds available memory, but at Q2_K it needs only 52.9 GB. Expected decode speed: 6.7 tok/s.

How much VRAM does Command A 111B need?

Command A 111B (111B parameters) requires approximately 77.3 GB at Q4_K_M quantization. On Radeon PRO W7900 DS 48GB, it fits at Q2_K using 52.9 GB.

What is the best quantization for Command A 111B?

The recommended quantization is Q4_K_M, but on Radeon PRO W7900 DS 48GB the best fitting quantization is Q2_K, which uses 52.9 GB.

What speed will Command A 111B run at on Radeon PRO W7900 DS 48GB?

On Radeon PRO W7900 DS 48GB, Command A 111B achieves approximately 6.7 tokens per second decode speed with a time-to-first-token of 28984ms using Q2_K quantization.

Can Radeon PRO W7900 DS 48GB run Command A 111B for coding?

For coding workloads, Command A 111B on Radeon PRO W7900 DS 48GB receives a F grade with 2.3 tok/s and 4K context.

What context window can Command A 111B use on Radeon PRO W7900 DS 48GB?

On Radeon PRO W7900 DS 48GB, Command A 111B can safely use up to 4K tokens of context at Q2_K quantization. The model's official context limit is 262K, but available memory constrains the safe maximum.

What should I upgrade first if Command A 111B feels slow on Radeon PRO W7900 DS 48GB?

Remove offload with more accelerator memory. Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.

See all results for Radeon PRO W7900 DS 48GB See all hardware for Command A 111B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/command-a-111b-on-radeon-pro-w7900-ds-48gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: