RTX 5090 32GB经济之选32 GB VRAM (+8)1792 GB/s (+1492)
B
Raises estimated decode speed by about 517%.82 tok/s 解码
Raises estimated decode speed by about 517%.
Adds memory headroom for longer context windows and future model growth.
~$1,999 MSRP
Can cognitivecomputations Dolphin3.0 R1 Mistral 24B run on NVIDIA L4 24GB?
YES — Tight Fit
C48Usable
Estimated from fit model
cognitivecomputations Dolphin3.0 R1 Mistral 24B needs ~21.1 GB VRAM. NVIDIA L4 24GB has 24.0 GB. With Q4_K_M quantization, expect ~13 tok/s.
Runtime: OllamaCapacity: TightBandwidth: LowStack: 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.
Select quantization to explore
Q4_K_M (Medium quality) — 21.1 GB, 13.3 tok/s, Tight fit
21.1 GB required24.0 GB available
88% VRAM used
Fit status
Tight fit
Decode
13.3 tok/s
TTFT
14535 ms
Safe context
33K
Memory
21.1 GB / 24.0 GB
Memory breakdown
Weights14.6 GB
KV Cache2.8 GB
Runtime1.2 GB
Headroom2.4 GB
See how fast it feels
See how fast it feelscognitivecomputations Dolphin3.0 R1 Mistral 24B on NVIDIA L4 24GB
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: 13.3 tok/s decode · 14.5s TTFT (warm) · 33 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 | 13.3 tok/s | 7928 ms | 33K |
| Coding | C | Tight fit | 13.3 tok/s | 14535 ms | 33K |
| Agentic Coding | C | Runs with offload | 13.3 tok/s | 21142 ms | 33K |
| Reasoning | C | Tight fit | 13.3 tok/s | 17178 ms | 33K |
| RAG | C | Runs with offload | 13.3 tok/s | 26427 ms | 33K |
Quantization options
How cognitivecomputations Dolphin3.0 R1 Mistral 24B (24B params) fits at each quantization level on NVIDIA L4 24GB (24.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 9.4 GB | Low | C49 |
Q3_K_S | 3 | 11.8 GB | Low | C50 |
NVFP4 | 4 | 13.4 GB | Medium | C50 |
Q4_K_M | 4 | 14.6 GB | Medium | C50 |
Q5_K_MBest for your GPU | 5 | 17.3 GB | High | C50 |
Q6_K | 6 | 19.7 GB | High | F0 |
Q8_0 | 8 | 25.7 GB | Very High | F0 |
F16 | 16 | 49.2 GB | Maximum | F0 |
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升级选项
能流畅运行 cognitivecomputations Dolphin3.0 R1 Mistral 24B 的硬件
RTX 5090 32GB经济之选RTX PRO 4500 Blackwell 32GB最佳性价比32 GB VRAM (+8)896 GB/s (+596)
C
Raises estimated decode speed by about 286%.51.4 tok/s 解码
Raises estimated decode speed by about 286%.
Adds memory headroom for longer context windows and future model growth.
~$2,499 MSRP
RTX 5000 Ada 32GBNVIDIA 升级32 GB VRAM (+8)576 GB/s (+276)
C
Raises estimated decode speed by about 137%.31.5 tok/s 解码
Raises estimated decode speed by about 137%.
Adds memory headroom for longer context windows and future model growth.
~$4,000 MSRP
Frequently asked questions
Can NVIDIA L4 24GB run cognitivecomputations Dolphin3.0 R1 Mistral 24B?
Yes, NVIDIA L4 24GB can run cognitivecomputations Dolphin3.0 R1 Mistral 24B with a C grade (Tight fit). Expected decode speed: 13.3 tok/s.
How much VRAM does cognitivecomputations Dolphin3.0 R1 Mistral 24B need?
cognitivecomputations Dolphin3.0 R1 Mistral 24B (24B parameters) requires approximately 21.1 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 L4 24GB?
On NVIDIA L4 24GB, cognitivecomputations Dolphin3.0 R1 Mistral 24B achieves approximately 13.3 tokens per second decode speed with a time-to-first-token of 14535ms using Q4_K_M quantization.
Can NVIDIA L4 24GB run cognitivecomputations Dolphin3.0 R1 Mistral 24B for coding?
For coding workloads, cognitivecomputations Dolphin3.0 R1 Mistral 24B on NVIDIA L4 24GB receives a C grade with 13.3 tok/s and 33K context.
What context window can cognitivecomputations Dolphin3.0 R1 Mistral 24B use on NVIDIA L4 24GB?
On NVIDIA L4 24GB, cognitivecomputations Dolphin3.0 R1 Mistral 24B can safely use up to 33K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.
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-l4-24gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: