VOOZH about

URL: https://willitrunai.com/can-run/codestral-2-25.08-on-rtx-pro-6000-blackwell-server-96gb

⇱ Codestral 2 25.08 on RTX PRO 6000 Blackwell Server Edition …

Can Codestral 2 25.08 run on RTX PRO 6000 Blackwell Server Edition 96GB?

YES — Runs Great

A82Great
○Estimated from fit model

Codestral 2 25.08 needs ~26.4 GB VRAM. RTX PRO 6000 Blackwell Server Edition 96GB has 96.0 GB. With Q4_K_M quantization, expect ~96 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: HighStack: StandardBottleneck: 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) — 26.4 GB, 96.0 tok/s, Runs well
26.4 GB required96.0 GB available
27% VRAM used

Fit status

Runs well

Decode

96.0 tok/s

TTFT

2018 ms

Safe context

256K

Memory

26.4 GB / 96.0 GB

Memory breakdown

Weights13.4 GB
KV Cache2.4 GB
Runtime0.9 GB
Headroom9.6 GB

See how fast it feels

See how fast it feelsCodestral 2 25.08 on RTX PRO 6000 Blackwell Server Edition 96GB
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: 96.0 tok/s decode · 2.0s TTFT (warm) · 240 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
ChatARuns well96.0 tok/s1100 ms256K
CodingARuns well96.0 tok/s2018 ms256K
Agentic CodingARuns well96.0 tok/s2935 ms256K
ReasoningARuns well96.0 tok/s2384 ms256K
RAGARuns well96.0 tok/s3668 ms256K

Quantization options

How Codestral 2 25.08 (22B params) fits at each quantization level on RTX PRO 6000 Blackwell Server Edition 96GB (96.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
8.6 GB
LowA74
Q3_K_S
3
10.8 GB
LowA74
NVFP4
4
12.3 GB
MediumA74
Q4_K_M
4
13.4 GB
MediumA74
Q5_K_M
5
15.8 GB
HighA74
Q6_K
6
18.0 GB
HighA75
Q8_0
8
23.5 GB
Very HighA75
F16Best for your GPU
16
45.1 GB
MaximumA80

Get started

Copy-paste commands to run Codestral 2 25.08 on your machine.

Run

lms load codestral-2508 && lms server start

Your hardware

More models your RTX PRO 6000 Blackwell Server Edition 96GB can run

ModelParamsGradeDecodeCapabilities
👁 Mistral
Devstral 2 123B Instruct		123BS19.4 tok/s
👁 Alibaba
Qwen3-Coder 30B A3B Instruct		30.5BS202.8 tok/s
👁 Alibaba
Qwen 3.5 27B		27BS88 tok/s
👁 Alibaba
Qwen 3.6 27B		27BS54.8 tok/s
👁 Alibaba
Qwen 3.5 122B A10B		122BS53.9 tok/s

Frequently asked questions

See all results for RTX PRO 6000 Blackwell Server Edition 96GBSee all hardware for Codestral 2 25.08