Will It Run AI

Can Magistral Small 2507 run on NVIDIA H100 80GB?

YES — Runs Great

S90Excellent
Estimated from fit model

Magistral Small 2507 needs ~26.3 GB VRAM. NVIDIA H100 80GB has 80.0 GB. With Q4_K_M quantization, expect ~207 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) — 26.3 GB, 206.6 tok/s, Runs well
26.3 GB required80.0 GB available
33% VRAM used

Fit status

Runs well

Decode

206.6 tok/s

TTFT

937 ms

Safe context

131K

Memory

26.3 GB / 80.0 GB

Memory breakdown

Weights14.6 GB
KV Cache2.4 GB
Runtime1.2 GB
Headroom8.0 GB

See how fast it feels

See how fast it feelsMagistral Small 2507 on NVIDIA H100 80GB
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: 206.6 tok/s decode · 937ms TTFT (warm) · 517 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 well206.6 tok/s511 ms131K
CodingSRuns well206.6 tok/s937 ms131K
Agentic CodingSRuns well206.6 tok/s1363 ms131K
ReasoningSRuns well206.6 tok/s1107 ms131K
RAGSRuns well206.6 tok/s1704 ms131K

Quantization options

How Magistral Small 2507 (24B params) fits at each quantization level on NVIDIA H100 80GB (80.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
9.4 GB
LowA82
Q3_K_S
3
11.8 GB
LowA82
NVFP4
4
13.4 GB
MediumA82
Q4_K_M
4
14.6 GB
MediumA82
Q5_K_M
5
17.3 GB
HighA83
Q6_K
6
19.7 GB
HighA83
Q8_0
8
25.7 GB
Very HighA84
F16Best for your GPU
16
49.2 GB
MaximumS89

Get started

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

Run

ollama run magistral

Your hardware

More models your NVIDIA H100 80GB can run

ModelParamsGradeDecodeCapabilities
MistralDevstral 2 123B Instruct123BA28.9 tok/s
AlibabaQwen3-Coder 30B A3B Instruct30.5BS425.5 tok/s
AlibabaQwen 3.5 27B27BS184.5 tok/s
AlibabaQwen 3.6 27B27BS185.1 tok/s
AlibabaQwen 3.5 122B A10B122BS85.5 tok/s

Frequently asked questions

Can NVIDIA H100 80GB run Magistral Small 2507?

Yes, NVIDIA H100 80GB can run Magistral Small 2507 with a S grade (Runs well). Expected decode speed: 206.6 tok/s.

How much VRAM does Magistral Small 2507 need?

Magistral Small 2507 (24B parameters) requires approximately 26.3 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 H100 80GB?

On NVIDIA H100 80GB, Magistral Small 2507 achieves approximately 206.6 tokens per second decode speed with a time-to-first-token of 937ms using Q4_K_M quantization.

Can NVIDIA H100 80GB run Magistral Small 2507 for coding?

For coding workloads, Magistral Small 2507 on NVIDIA H100 80GB receives a S grade with 206.6 tok/s and 131K context.

What context window can Magistral Small 2507 use on NVIDIA H100 80GB?

On NVIDIA H100 80GB, 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 H100 80GBSee 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-h100-80gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: