Can Codestral RAG 19B Pruned i1 run on AMD Instinct MI350X 288GB?

YES — Runs Great

C45Usable

Estimated from fit model

Codestral RAG 19B Pruned i1 needs ~43.5 GB VRAM. AMD Instinct MI350X 288GB has 288.0 GB. With Q4_K_M quantization, expect ~266 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) — 43.5 GB, 266.0 tok/s, Runs well

43.5 GB required288.0 GB available

15% VRAM used

Fit status

Runs well

Decode

266.0 tok/s

TTFT

728 ms

Safe context

1.8M

Memory

43.5 GB / 288.0 GB

Memory breakdown

Weights11.6 GB

KV Cache2.2 GB

Runtime0.9 GB

Headroom28.8 GB

See how fast it feels

See how fast it feelsCodestral RAG 19B Pruned i1 on AMD Instinct MI350X 288GB
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: 266.0 tok/s decode · 728ms TTFT (warm) · 665 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	266.0 tok/s	397 ms	1.8M
Coding	C	Runs well	266.0 tok/s	728 ms	1.8M
Agentic Coding	C	Runs well	266.0 tok/s	1059 ms	1.8M
Reasoning	C	Runs well	266.0 tok/s	860 ms	1.8M
RAG	C	Runs well	266.0 tok/s	1323 ms	1.8M

Inference speed

Codestral RAG 19B Pruned i1 inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Codestral RAG 19B 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 ~104 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	103.6	Fits
RTX 4090 24GB	24 GB	Q4_K_M	66.1	Fits
RX 7900 XTX 24GB	24 GB	Q4_K_M	59.6	Fits
RTX 3090 24GB	24 GB	Q4_K_M	56.5	Fits
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	48.1	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	40.0	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	38.0	Fits
RTX 4080 Super 16GB	16 GB	Q4_K_M	36.5	Offloads
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	36.0	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	36.0	Fits
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	22.7	Fits
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	20.7	Fits
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	19.0	Fits
RTX 4070 12GB	12 GB	Q4_K_M	13.0	Too big
RTX 3060 12GB	12 GB	Q4_K_M	8.2	Too big
RTX 4060 8GB	8 GB	Q4_K_M	3.1	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 RAG 19B Pruned i1 (19B params) fits at each quantization level on AMD Instinct MI350X 288GB (288.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	7.4 GB	Low	D35
Q3_K_S	3	9.3 GB	Low	D35
NVFP4	4	10.6 GB	Medium	D35
Q4_K_M	4	11.6 GB	Medium	D35
Q5_K_M	5	13.7 GB	High	D36
Q6_K	6	15.6 GB	High	D36
Q8_0	8	20.3 GB	Very High	D36
F16Best for your GPU	16	38.9 GB	Maximum	D37

Get started

Copy-paste commands to run Codestral RAG 19B Pruned i1 on your machine.

Run

lms load hf-mradermacher--codestral-rag-19b-pruned-i1-gguf && lms server start

Frequently asked questions

Can AMD Instinct MI350X 288GB run Codestral RAG 19B Pruned i1?

Yes, AMD Instinct MI350X 288GB can run Codestral RAG 19B Pruned i1 with a C grade (Runs well). Expected decode speed: 266.0 tok/s.

How much VRAM does Codestral RAG 19B Pruned i1 need?

Codestral RAG 19B Pruned i1 (19B parameters) requires approximately 43.5 GB of memory with Q4_K_M quantization.

What is the best quantization for Codestral RAG 19B Pruned i1?

The recommended quantization for Codestral RAG 19B Pruned i1 is Q4_K_M, which balances quality and memory efficiency.

What speed will Codestral RAG 19B Pruned i1 run at on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, Codestral RAG 19B Pruned i1 achieves approximately 266.0 tokens per second decode speed with a time-to-first-token of 728ms using Q4_K_M quantization.

Can AMD Instinct MI350X 288GB run Codestral RAG 19B Pruned i1 for coding?

For coding workloads, Codestral RAG 19B Pruned i1 on AMD Instinct MI350X 288GB receives a C grade with 266.0 tok/s and 1.8M context.

What context window can Codestral RAG 19B Pruned i1 use on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, Codestral RAG 19B Pruned i1 can safely use up to 1.8M tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

See all results for AMD Instinct MI350X 288GB See all hardware for Codestral RAG 19B 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-rag-19b-pruned-i1-gguf-on-instinct-mi350x-288gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: