Will It Run AI

Can Magistral Small 2507 run on NVIDIA GB200 192GB?

YES — Runs Great

S88Excellent
Estimated from fit model

Magistral Small 2507 needs ~37.5 GB VRAM. NVIDIA GB200 192GB has 192.0 GB. With Q4_K_M quantization, expect ~336 tok/s.

Runtime: OllamaCapacity: RoomyBandwidth: HighStack: 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) — 37.5 GB, 336.0 tok/s, Runs well
37.5 GB required192.0 GB available
20% VRAM used

Fit status

Runs well

Decode

336.0 tok/s

TTFT

576 ms

Safe context

131K

Memory

37.5 GB / 192.0 GB

Memory breakdown

Weights14.6 GB
KV Cache2.4 GB
Runtime1.2 GB
Headroom19.2 GB

See how fast it feels

See how fast it feelsMagistral Small 2507 on NVIDIA GB200 192GB
1st promptCold start — includes initialization
>Solve: If a train travels at 60 mph for 2.5 hours, how far does it go?
Let me work through this step by step. Given information: - Speed = 60 mph (miles per hour) - Time = 2.5 hours Formula: Distance = Speed x Time Calculation: Distance = 60 mph x 2.5 h = 150 miles The train travels 150 miles. Double-check: at 60 mph the train covers 60 miles each hour. In half an hour it covers 30 miles. So in 2.5 hours: 60 + 60 + 30 = 150 miles. Confirmed.
2nd promptWarm — model ready, no init overhead
>What if the train stops for 20 minutes halfway?
The stop doesn't change the total distance covered while moving, but it affects total trip time. Breakdown: - First half: 1.25 hours at 60 mph = 75 miles - Stop: 20 minutes (no distance) - Second half: 1.25 hours at 60 mph = 75 miles Total distance: 150 miles (same) Total time: 2.5 h + 0.33 h = 2.83 hours Average speed: 150 / 2.83 = 53 mph The distance stays the same but average speed drops to 53 mph because of the stop.
Estimated: 336.0 tok/s decode · 576ms TTFT (warm) · 840 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
ChatSRuns well336.0 tok/s350 ms131K
CodingSRuns well336.0 tok/s576 ms131K
Agentic CodingSRuns well336.0 tok/s838 ms131K
ReasoningSRuns well336.0 tok/s681 ms131K
RAGSRuns well336.0 tok/s1048 ms131K

Quantization options

How Magistral Small 2507 (24B params) fits at each quantization level on NVIDIA GB200 192GB (192.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
9.4 GB
LowA78
Q3_K_S
3
11.8 GB
LowA79
NVFP4
4
13.4 GB
MediumA79
Q4_K_M
4
14.6 GB
MediumA79
Q5_K_M
5
17.3 GB
HighA79
Q6_K
6
19.7 GB
HighA79
Q8_0
8
25.7 GB
Very HighA80
F16Best for your GPU
16
49.2 GB
MaximumA82

Get started

Copy-paste commands to run Magistral Small 2507 on your machine.

Run

ollama run magistral

Your hardware

More models your NVIDIA GB200 192GB can run

ModelParamsGradeDecodeCapabilities
MistralDevstral 2 123B Instruct123BS97.4 tok/s
AlibabaQwen3-Coder 30B A3B Instruct30.5BS1016.1 tok/s
AlibabaQwen 3.5 27B27BS378 tok/s
AlibabaQwen 3.6 27B27BS378 tok/s
AlibabaQwen 3.5 122B A10B122BS270.2 tok/s

Frequently asked questions

Can NVIDIA GB200 192GB run Magistral Small 2507?

Yes, NVIDIA GB200 192GB can run Magistral Small 2507 with a S grade (Runs well). Expected decode speed: 336.0 tok/s.

How much VRAM does Magistral Small 2507 need?

Magistral Small 2507 (24B parameters) requires approximately 37.5 GB of memory with Q4_K_M quantization.

What is the best quantization for Magistral Small 2507?

The recommended quantization for Magistral Small 2507 is Q4_K_M, which balances quality and memory efficiency.

What speed will Magistral Small 2507 run at on NVIDIA GB200 192GB?

On NVIDIA GB200 192GB, Magistral Small 2507 achieves approximately 336.0 tokens per second decode speed with a time-to-first-token of 576ms using Q4_K_M quantization.

Can NVIDIA GB200 192GB run Magistral Small 2507 for coding?

For coding workloads, Magistral Small 2507 on NVIDIA GB200 192GB receives a S grade with 336.0 tok/s and 131K context.

What context window can Magistral Small 2507 use on NVIDIA GB200 192GB?

On NVIDIA GB200 192GB, Magistral Small 2507 can safely use up to 131K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.

See all results for NVIDIA GB200 192GBSee all hardware for Magistral Small 2507
Embed this result▼

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

<iframe src="https://willitrunai.com/embed/magistral-small-2507-on-gb200-192gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: