Can Codestral 21B Pruned i1 run on Radeon AI PRO R9700 32GB?

YES — Runs Great

C51Usable

Estimated from fit model

Codestral 21B Pruned i1 needs ~19.4 GB VRAM. Radeon AI PRO R9700 32GB has 32.0 GB. With Q4_K_M quantization, expect ~30 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: MediumStack: 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) — 19.4 GB, 29.5 tok/s, Runs well

19.4 GB required32.0 GB available

61% VRAM used

Fit status

Runs well

Decode

29.5 tok/s

TTFT

6568 ms

Safe context

98K

Memory

19.4 GB / 32.0 GB

Memory breakdown

Weights12.8 GB

KV Cache2.5 GB

Runtime0.9 GB

Headroom3.2 GB

See how fast it feels

See how fast it feelsCodestral 21B Pruned i1 on Radeon AI PRO R9700 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: 29.5 tok/s decode · 6.6s TTFT (warm) · 74 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	C	Runs well	29.5 tok/s	3582 ms	98K
Coding	C	Runs well	29.5 tok/s	6568 ms	98K
Agentic Coding	C	Runs well	29.5 tok/s	9553 ms	98K
Reasoning	C	Runs well	29.5 tok/s	7762 ms	98K
RAG	C	Runs well	29.5 tok/s	11942 ms	98K

Inference speed

Codestral 21B Pruned i1 inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Codestral 21B Pruned i1 at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~94 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	93.7	Fits
RTX 4090 24GB	24 GB	Q4_K_M	59.8	Fits
RX 7900 XTX 24GB	24 GB	Q4_K_M	54.0	Fits
RTX 3090 24GB	24 GB	Q4_K_M	51.1	Fits
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	43.5	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	36.2	Fits
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	35.2	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	35.2	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	34.3	Fits
RTX 4080 Super 16GB	16 GB	Q4_K_M	27.7	Heavy offload
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	22.2	Fits
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	18.7	Fits
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	17.2	Fits
RTX 4070 12GB	12 GB	Q4_K_M	9.8	Too big
RTX 3060 12GB	12 GB	Q4_K_M	6.2	Too big
RTX 4060 8GB	8 GB	Q4_K_M	2.3	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 Codestral 21B Pruned i1 (21B params) fits at each quantization level on Radeon AI PRO R9700 32GB (32.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.2 GB	Low	C45
Q3_K_S	3	10.3 GB	Low	C46
NVFP4	4	11.8 GB	Medium	C46
Q4_K_M	4	12.8 GB	Medium	C47
Q5_K_M	5	15.1 GB	High	C48
Q6_K	6	17.2 GB	High	C49
Q8_0Best for your GPU	8	22.5 GB	Very High	C48
F16	16	43.1 GB	Maximum	F0

Get started

Copy-paste commands to run Codestral 21B Pruned i1 on your machine.

Run

lms load hf-mradermacher--codestral-21b-pruned-i1-gguf && lms server start

Upgrade options

Hardware that runs Codestral 21B Pruned i1 well

MacBook Pro M4 Max 48GBBudget pick

48 GB Unified (+16)

This setup is broadly balanced for this model.35.2 tok/s decode

~$2,499 MSRP

NVIDIA A100 40GBBest value

40 GB VRAM (+8)1555 GB/s (+915)

Raises estimated decode speed by about 246%.102 tok/s decode

Raises estimated decode speed by about 246%.

Adds memory headroom for longer context windows and future model growth.

~$10,000 MSRP

Frequently asked questions

Can Radeon AI PRO R9700 32GB run Codestral 21B Pruned i1?

Yes, Radeon AI PRO R9700 32GB can run Codestral 21B Pruned i1 with a C grade (Runs well). Expected decode speed: 29.5 tok/s.

How much VRAM does Codestral 21B Pruned i1 need?

Codestral 21B Pruned i1 (21B parameters) requires approximately 19.4 GB of memory with Q4_K_M quantization.

What is the best quantization for Codestral 21B Pruned i1?

The recommended quantization for Codestral 21B Pruned i1 is Q4_K_M, which balances quality and memory efficiency.

What speed will Codestral 21B Pruned i1 run at on Radeon AI PRO R9700 32GB?

On Radeon AI PRO R9700 32GB, Codestral 21B Pruned i1 achieves approximately 29.5 tokens per second decode speed with a time-to-first-token of 6568ms using Q4_K_M quantization.

Can Radeon AI PRO R9700 32GB run Codestral 21B Pruned i1 for coding?

For coding workloads, Codestral 21B Pruned i1 on Radeon AI PRO R9700 32GB receives a C grade with 29.5 tok/s and 98K context.

What context window can Codestral 21B Pruned i1 use on Radeon AI PRO R9700 32GB?

On Radeon AI PRO R9700 32GB, Codestral 21B Pruned i1 can safely use up to 98K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

See all results for Radeon AI PRO R9700 32GB See all hardware for Codestral 21B Pruned i1

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/hf-mradermacher--codestral-21b-pruned-i1-gguf-on-radeon-ai-pro-r9700-32gb" 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

29.5 tok/s

3582 ms

98K

Coding

Runs well

29.5 tok/s

6568 ms

98K

Agentic Coding

Runs well

29.5 tok/s

9553 ms

98K

Reasoning

Runs well

29.5 tok/s

7762 ms

98K

RAG

Runs well

29.5 tok/s

11942 ms

98K

Codestral 21B Pruned i1 inference speed — tokens per second by GPU & Mac

GPU / Mac

Memory

Quant

Speed (tok/s)

Fits?

RTX 5090 32GB

32 GB

Q4_K_M

93.7

Fits

RTX 4090 24GB

24 GB

Q4_K_M

59.8

Fits

RX 7900 XTX 24GB

24 GB

Q4_K_M

54.0

Fits

RTX 3090 24GB

24 GB

Q4_K_M

51.1

Fits

Mac Studio M3 Ultra 256GB

256 GB

Q4_K_M

43.5

Fits

Mac Studio M2 Ultra 128GB

128 GB

Q4_K_M

36.2

Fits

MacBook Pro M4 Max 128GB

128 GB

Q4_K_M

35.2

Fits

MacBook Pro M4 Max 64GB

64 GB

Q4_K_M

35.2

Fits

Mac Studio M1 Ultra 128GB

128 GB

Q4_K_M

34.3

Fits

RTX 4080 Super 16GB

16 GB

Q4_K_M

27.7

Heavy offload

MacBook Pro M4 Pro 48GB

48 GB

Q4_K_M

22.2

Fits

MacBook Pro M3 Max 64GB

64 GB

Q4_K_M

18.7

Fits

MacBook Pro M1 Max 64GB

64 GB

Q4_K_M

17.2

Fits

RTX 4070 12GB

12 GB

Q4_K_M

9.8

Too big

RTX 3060 12GB

12 GB

Q4_K_M

6.2

Too big

RTX 4060 8GB

8 GB

Q4_K_M

2.3

Too big

Quantization options

How Codestral 21B Pruned i1 (21B params) fits at each quantization level on Radeon AI PRO R9700 32GB (32.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.2 GB	Low	C45
Q3_K_S	3	10.3 GB	Low	C46
NVFP4	4	11.8 GB	Medium	C46
Q4_K_M	4	12.8 GB	Medium	C47
Q5_K_M	5	15.1 GB	High	C48
Q6_K	6	17.2 GB	High	C49
Q8_0Best for your GPU	8	22.5 GB	Very High	C48
F16	16	43.1 GB	Maximum	F0

Frequently asked questions

Can Radeon AI PRO R9700 32GB run Codestral 21B Pruned i1?

Yes, Radeon AI PRO R9700 32GB can run Codestral 21B Pruned i1 with a C grade (Runs well). Expected decode speed: 29.5 tok/s.

How much VRAM does Codestral 21B Pruned i1 need?

Codestral 21B Pruned i1 (21B parameters) requires approximately 19.4 GB of memory with Q4_K_M quantization.

What is the best quantization for Codestral 21B Pruned i1?

The recommended quantization for Codestral 21B Pruned i1 is Q4_K_M, which balances quality and memory efficiency.

What speed will Codestral 21B Pruned i1 run at on Radeon AI PRO R9700 32GB?

On Radeon AI PRO R9700 32GB, Codestral 21B Pruned i1 achieves approximately 29.5 tokens per second decode speed with a time-to-first-token of 6568ms using Q4_K_M quantization.

Can Radeon AI PRO R9700 32GB run Codestral 21B Pruned i1 for coding?

For coding workloads, Codestral 21B Pruned i1 on Radeon AI PRO R9700 32GB receives a C grade with 29.5 tok/s and 98K context.

What context window can Codestral 21B Pruned i1 use on Radeon AI PRO R9700 32GB?

On Radeon AI PRO R9700 32GB, Codestral 21B Pruned i1 can safely use up to 98K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.