Can cognitivecomputations Dolphin3.0 R1 Mistral 24B run on NVIDIA H200 PCIe 141GB?

YES — Runs Great

C47Usable

Estimated from fit model

cognitivecomputations Dolphin3.0 R1 Mistral 24B needs ~32.8 GB VRAM. NVIDIA H200 PCIe 141GB has 141.0 GB. With Q4_K_M quantization, expect ~275 tok/s.

Runtime: OllamaCapacity: RoomyBandwidth: HighStack: BasicBottleneck: Balanced

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) — 32.8 GB, 275.4 tok/s, Runs well

32.8 GB required141.0 GB available

23% VRAM used

Fit status

Runs well

Decode

275.4 tok/s

TTFT

703 ms

Safe context

632K

Memory

32.8 GB / 141.0 GB

Memory breakdown

Weights14.6 GB

KV Cache2.8 GB

Runtime1.2 GB

Headroom14.1 GB

See how fast it feels

See how fast it feelscognitivecomputations Dolphin3.0 R1 Mistral 24B on NVIDIA H200 PCIe 141GB
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: 275.4 tok/s decode · 703ms TTFT (warm) · 689 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

Workload	Grade	Fit	Decode	TTFT	Context
Chat	C	Runs well	275.4 tok/s	383 ms	632K
Coding	C	Runs well	275.4 tok/s	703 ms	632K
Agentic Coding	C	Runs well	275.4 tok/s	1022 ms	632K
Reasoning	C	Runs well	275.4 tok/s	831 ms	632K
RAG	C	Runs well	275.4 tok/s	1278 ms	632K

Quantization options

How cognitivecomputations Dolphin3.0 R1 Mistral 24B (24B params) fits at each quantization level on NVIDIA H200 PCIe 141GB (141.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	9.4 GB	Low	D38
Q3_K_S	3	11.8 GB	Low	D38
NVFP4	4	13.4 GB	Medium	D38
Q4_K_M	4	14.6 GB	Medium	D38
Q5_K_M	5	17.3 GB	High	D38
Q6_K	6	19.7 GB	High	D39
Q8_0	8	25.7 GB	Very High	D39
F16Best for your GPU	16	49.2 GB	Maximum	C43

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 H200 PCIe 141GB run cognitivecomputations Dolphin3.0 R1 Mistral 24B?

Yes, NVIDIA H200 PCIe 141GB can run cognitivecomputations Dolphin3.0 R1 Mistral 24B with a C grade (Runs well). Expected decode speed: 275.4 tok/s.

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

cognitivecomputations Dolphin3.0 R1 Mistral 24B (24B parameters) requires approximately 32.8 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 H200 PCIe 141GB?

On NVIDIA H200 PCIe 141GB, cognitivecomputations Dolphin3.0 R1 Mistral 24B achieves approximately 275.4 tokens per second decode speed with a time-to-first-token of 703ms using Q4_K_M quantization.

Can NVIDIA H200 PCIe 141GB run cognitivecomputations Dolphin3.0 R1 Mistral 24B for coding?

For coding workloads, cognitivecomputations Dolphin3.0 R1 Mistral 24B on NVIDIA H200 PCIe 141GB receives a C grade with 275.4 tok/s and 632K context.

What context window can cognitivecomputations Dolphin3.0 R1 Mistral 24B use on NVIDIA H200 PCIe 141GB?

On NVIDIA H200 PCIe 141GB, cognitivecomputations Dolphin3.0 R1 Mistral 24B can safely use up to 632K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

See all results for NVIDIA H200 PCIe 141GB See 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-h200-pcie-141gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: