Will It Run AI

Can cognitivecomputations Dolphin3.0 R1 Mistral 24B run on NVIDIA A100 80GB?

YES — Runs Great

C49Usable
Estimated from fit model

cognitivecomputations Dolphin3.0 R1 Mistral 24B needs ~26.7 GB VRAM. NVIDIA A100 80GB has 80.0 GB. With Q4_K_M quantization, expect ~117 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) — 26.7 GB, 117.0 tok/s, Runs well
26.7 GB required80.0 GB available
33% VRAM used

Fit status

Runs well

Decode

117.0 tok/s

TTFT

1655 ms

Safe context

319K

Memory

26.7 GB / 80.0 GB

Memory breakdown

Weights14.6 GB
KV Cache2.8 GB
Runtime1.2 GB
Headroom8.0 GB

See how fast it feels

See how fast it feelscognitivecomputations Dolphin3.0 R1 Mistral 24B on NVIDIA A100 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: 117.0 tok/s decode · 1.7s TTFT (warm) · 293 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 well117.0 tok/s903 ms319K
CodingCRuns well117.0 tok/s1655 ms319K
Agentic CodingCRuns well117.0 tok/s2407 ms319K
ReasoningCRuns well117.0 tok/s1956 ms319K
RAGCRuns well117.0 tok/s3009 ms319K

Quantization options

How cognitivecomputations Dolphin3.0 R1 Mistral 24B (24B params) fits at each quantization level on NVIDIA A100 80GB (80.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
9.4 GB
LowC40
Q3_K_S
3
11.8 GB
LowC40
NVFP4
4
13.4 GB
MediumC41
Q4_K_M
4
14.6 GB
MediumC41
Q5_K_M
5
17.3 GB
HighC41
Q6_K
6
19.7 GB
HighC42
Q8_0
8
25.7 GB
Very HighC43
F16Best for your GPU
16
49.2 GB
MaximumC48

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 A100 80GB run cognitivecomputations Dolphin3.0 R1 Mistral 24B?

Yes, NVIDIA A100 80GB can run cognitivecomputations Dolphin3.0 R1 Mistral 24B with a C grade (Runs well). Expected decode speed: 117.0 tok/s.

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

cognitivecomputations Dolphin3.0 R1 Mistral 24B (24B parameters) requires approximately 26.7 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 A100 80GB?

On NVIDIA A100 80GB, cognitivecomputations Dolphin3.0 R1 Mistral 24B achieves approximately 117.0 tokens per second decode speed with a time-to-first-token of 1655ms using Q4_K_M quantization.

Can NVIDIA A100 80GB run cognitivecomputations Dolphin3.0 R1 Mistral 24B for coding?

For coding workloads, cognitivecomputations Dolphin3.0 R1 Mistral 24B on NVIDIA A100 80GB receives a C grade with 117.0 tok/s and 319K context.

What context window can cognitivecomputations Dolphin3.0 R1 Mistral 24B use on NVIDIA A100 80GB?

On NVIDIA A100 80GB, cognitivecomputations Dolphin3.0 R1 Mistral 24B can safely use up to 319K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

See all results for NVIDIA A100 80GBSee 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-a100-80gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: