Can Codestral RAG 19B Pruned i1 run on NVIDIA A16 64GB?

YES — Runs Great

C46Usable

Estimated from fit model

Codestral RAG 19B Pruned i1 needs ~21.4 GB VRAM. NVIDIA A16 64GB has 64.0 GB. With Q4_K_M quantization, expect ~40 tok/s.

Runtime: OllamaCapacity: RoomyBandwidth: MediumStack: BasicBottleneck: 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) — 21.4 GB, 40.4 tok/s, Runs well

21.4 GB required64.0 GB available

33% VRAM used

Fit status

Runs well

Decode

40.4 tok/s

TTFT

4794 ms

Safe context

322K

Memory

21.4 GB / 64.0 GB

Memory breakdown

Weights11.6 GB

KV Cache2.2 GB

Runtime1.2 GB

Headroom6.4 GB

See how fast it feels

See how fast it feelsCodestral RAG 19B Pruned i1 on NVIDIA A16 64GB
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: 40.4 tok/s decode · 4.8s TTFT (warm) · 101 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	40.4 tok/s	2615 ms	322K
Coding	C	Runs well	40.4 tok/s	4794 ms	322K
Agentic Coding	C	Runs well	40.4 tok/s	6974 ms	322K
Reasoning	C	Runs well	40.4 tok/s	5666 ms	322K
RAG	C	Runs well	40.4 tok/s	8717 ms	322K

Quantization options

How Codestral RAG 19B Pruned i1 (19B params) fits at each quantization level on NVIDIA A16 64GB (64.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	7.4 GB	Low	C40
Q3_K_S	3	9.3 GB	Low	C41
NVFP4	4	10.6 GB	Medium	C41
Q4_K_M	4	11.6 GB	Medium	C41
Q5_K_M	5	13.7 GB	High	C41
Q6_K	6	15.6 GB	High	C42
Q8_0	8	20.3 GB	Very High	C43
F16Best for your GPU	16	38.9 GB	Maximum	C47

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

Upgrade-Optionen

Hardware, die Codestral RAG 19B Pruned i1 gut ausführt

RTX PRO 6000 Blackwell Workstation Edition 96GBGünstige Wahl

96 GB VRAM (+32)1792 GB/s (+1192)

Raises estimated decode speed by about 222%.129.9 tok/s Dekodierung

Raises estimated decode speed by about 222%.

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

ca. $9,999 MSRP

RTX PRO 6000 Blackwell Server Edition 96GBBestes Preis-Leistungs-Verhältnis

96 GB VRAM (+32)1597 GB/s (+997)

Raises estimated decode speed by about 186%.115.7 tok/s Dekodierung

Raises estimated decode speed by about 186%.

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

ca. $9,999 MSRP

NVIDIA H20 96GBNVIDIA-Upgrade

96 GB VRAM (+32)4000 GB/s (+3400)

Raises estimated decode speed by about 558%.266 tok/s Dekodierung

Raises estimated decode speed by about 558%.

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

ca. $12,000 MSRP

Frequently asked questions

Can NVIDIA A16 64GB run Codestral RAG 19B Pruned i1?

Yes, NVIDIA A16 64GB can run Codestral RAG 19B Pruned i1 with a C grade (Runs well). Expected decode speed: 40.4 tok/s.

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

Codestral RAG 19B Pruned i1 (19B parameters) requires approximately 21.4 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 NVIDIA A16 64GB?

On NVIDIA A16 64GB, Codestral RAG 19B Pruned i1 achieves approximately 40.4 tokens per second decode speed with a time-to-first-token of 4794ms using Q4_K_M quantization.

Can NVIDIA A16 64GB run Codestral RAG 19B Pruned i1 for coding?

For coding workloads, Codestral RAG 19B Pruned i1 on NVIDIA A16 64GB receives a C grade with 40.4 tok/s and 322K context.

What context window can Codestral RAG 19B Pruned i1 use on NVIDIA A16 64GB?

On NVIDIA A16 64GB, Codestral RAG 19B Pruned i1 can safely use up to 322K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

See all results for NVIDIA A16 64GB 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-a16-64gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: