Will It Run AI

Can cognitivecomputations Dolphin3.0 R1 Mistral 24B run on NVIDIA GB200 192GB?

YES — Runs Great

C46Usable
Estimated from fit model

cognitivecomputations Dolphin3.0 R1 Mistral 24B needs ~37.9 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) — 37.9 GB, 336.0 tok/s, Runs well
37.9 GB required192.0 GB available
20% VRAM used

Fit status

Runs well

Decode

336.0 tok/s

TTFT

576 ms

Safe context

893K

Memory

37.9 GB / 192.0 GB

Memory breakdown

Weights14.6 GB
KV Cache2.8 GB
Runtime1.2 GB
Headroom19.2 GB

See how fast it feels

See how fast it feelscognitivecomputations Dolphin3.0 R1 Mistral 24B 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
ChatCRuns well336.0 tok/s350 ms893K
CodingCRuns well336.0 tok/s576 ms893K
Agentic CodingCRuns well336.0 tok/s838 ms893K
ReasoningCRuns well336.0 tok/s681 ms893K
RAGCRuns well336.0 tok/s1048 ms893K

Quantization options

How cognitivecomputations Dolphin3.0 R1 Mistral 24B (24B params) fits at each quantization level on NVIDIA GB200 192GB (192.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
9.4 GB
LowD37
Q3_K_S
3
11.8 GB
LowD37
NVFP4
4
13.4 GB
MediumD37
Q4_K_M
4
14.6 GB
MediumD37
Q5_K_M
5
17.3 GB
HighD37
Q6_K
6
19.7 GB
HighD37
Q8_0
8
25.7 GB
Very HighD38
F16Best for your GPU
16
49.2 GB
MaximumC41

Get started

Copy-paste commands to run cognitivecomputations Dolphin3.0 R1 Mistral 24B on your machine.

Run

lms load hf-bartowski--cognitivecomputations-dolphin3-0-r1-mistral-24b-gguf && lms server start

Frequently asked questions

Can NVIDIA GB200 192GB run cognitivecomputations Dolphin3.0 R1 Mistral 24B?

Yes, NVIDIA GB200 192GB can run cognitivecomputations Dolphin3.0 R1 Mistral 24B with a C grade (Runs well). Expected decode speed: 336.0 tok/s.

How much VRAM does cognitivecomputations Dolphin3.0 R1 Mistral 24B need?

cognitivecomputations Dolphin3.0 R1 Mistral 24B (24B parameters) requires approximately 37.9 GB of memory with Q4_K_M quantization.

What is the best quantization for cognitivecomputations Dolphin3.0 R1 Mistral 24B?

The recommended quantization for cognitivecomputations Dolphin3.0 R1 Mistral 24B is Q4_K_M, which balances quality and memory efficiency.

What speed will cognitivecomputations Dolphin3.0 R1 Mistral 24B run at on NVIDIA GB200 192GB?

On NVIDIA GB200 192GB, cognitivecomputations Dolphin3.0 R1 Mistral 24B 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 cognitivecomputations Dolphin3.0 R1 Mistral 24B for coding?

For coding workloads, cognitivecomputations Dolphin3.0 R1 Mistral 24B on NVIDIA GB200 192GB receives a C grade with 336.0 tok/s and 893K context.

What context window can cognitivecomputations Dolphin3.0 R1 Mistral 24B use on NVIDIA GB200 192GB?

On NVIDIA GB200 192GB, cognitivecomputations Dolphin3.0 R1 Mistral 24B can safely use up to 893K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

See all results for NVIDIA GB200 192GBSee all hardware for cognitivecomputations Dolphin3.0 R1 Mistral 24B
Embed this result▼

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

<iframe src="https://willitrunai.com/embed/hf-bartowski--cognitivecomputations-dolphin3-0-r1-mistral-24b-gguf-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: