Will It Run AI

Can Codestral 21B Pruned i1 run on NVIDIA A16 64GB?

YES — Runs Great

C46Usable
Estimated from fit model

Codestral 21B Pruned i1 needs ~22.9 GB VRAM. NVIDIA A16 64GB has 64.0 GB. With Q4_K_M quantization, expect ~37 tok/s.

Runtime: OllamaCapacity: RoomyBandwidth: MediumStack: BasicBottleneck: Balanced
Share:

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) — 22.9 GB, 36.5 tok/s, Runs well
22.9 GB required64.0 GB available
36% VRAM used

Fit status

Runs well

Decode

36.5 tok/s

TTFT

5299 ms

Safe context

283K

Memory

22.9 GB / 64.0 GB

Memory breakdown

Weights12.8 GB
KV Cache2.5 GB
Runtime1.2 GB
Headroom6.4 GB

See how fast it feels

See how fast it feelsCodestral 21B 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: 36.5 tok/s decode · 5.3s TTFT (warm) · 91 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

WorkloadGradeFitDecodeTTFTContext
ChatCRuns well36.5 tok/s2890 ms283K
CodingCRuns well36.5 tok/s5299 ms283K
Agentic CodingCRuns well36.5 tok/s7708 ms283K
ReasoningCRuns well36.5 tok/s6263 ms283K
RAGCRuns well36.5 tok/s9635 ms283K

Quantization options

How Codestral 21B Pruned i1 (21B params) fits at each quantization level on NVIDIA A16 64GB (64.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
8.2 GB
LowC41
Q3_K_S
3
10.3 GB
LowC41
NVFP4
4
11.8 GB
MediumC41
Q4_K_M
4
12.8 GB
MediumC41
Q5_K_M
5
15.1 GB
HighC42
Q6_K
6
17.2 GB
HighC42
Q8_0
8
22.5 GB
Very HighC43
F16Best for your GPU
16
43.1 GB
MaximumC47

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

Opciones de mejora

Hardware que ejecuta bien Codestral 21B Pruned i1

NVIDIARTX PRO 6000 Blackwell Workstation Edition 96GBOpción económica
96 GB VRAM (+32)1792 GB/s (+1192)
C
Sube la velocidad estimada de decodificación alrededor de un 222%.117.5 tok/s decodificación

Sube la velocidad estimada de decodificación alrededor de un 222%.

Añade margen de memoria para más contexto y para que el modelo envejezca mejor.

~$9,999 MSRP

NVIDIARTX PRO 6000 Blackwell Server Edition 96GBMejor relación calidad-precio
96 GB VRAM (+32)1597 GB/s (+997)
C
Sube la velocidad estimada de decodificación alrededor de un 187%.104.7 tok/s decodificación

Sube la velocidad estimada de decodificación alrededor de un 187%.

Añade margen de memoria para más contexto y para que el modelo envejezca mejor.

~$9,999 MSRP

NVIDIANVIDIA H20 96GBMejora NVIDIA
96 GB VRAM (+32)4000 GB/s (+3400)
C
Sube la velocidad estimada de decodificación alrededor de un 593%.252.9 tok/s decodificación

Sube la velocidad estimada de decodificación alrededor de un 593%.

Añade margen de memoria para más contexto y para que el modelo envejezca mejor.

~$12,000 MSRP

Frequently asked questions

Can NVIDIA A16 64GB run Codestral 21B Pruned i1?

Yes, NVIDIA A16 64GB can run Codestral 21B Pruned i1 with a C grade (Runs well). Expected decode speed: 36.5 tok/s.

How much VRAM does Codestral 21B Pruned i1 need?

Codestral 21B Pruned i1 (21B parameters) requires approximately 22.9 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 NVIDIA A16 64GB?

On NVIDIA A16 64GB, Codestral 21B Pruned i1 achieves approximately 36.5 tokens per second decode speed with a time-to-first-token of 5299ms using Q4_K_M quantization.

Can NVIDIA A16 64GB run Codestral 21B Pruned i1 for coding?

For coding workloads, Codestral 21B Pruned i1 on NVIDIA A16 64GB receives a C grade with 36.5 tok/s and 283K context.

What context window can Codestral 21B Pruned i1 use on NVIDIA A16 64GB?

On NVIDIA A16 64GB, Codestral 21B Pruned i1 can safely use up to 283K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

See all results for NVIDIA A16 64GBSee 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-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: