MacBook Pro M4 Pro 64GBBudget pick
64 GB Unified (+40)
C
Raises estimated decode speed by about 28%.21.5 tok/s decode
Raises estimated decode speed by about 28%.
Adds memory headroom for longer context windows and future model growth.
~$1,599 MSRP
Can cognitivecomputations Dolphin3.0 R1 Mistral 24B run on Intel Arc Pro B60 24GB?
YES — Tight Fit
C48Usable
○Estimated from fit model
cognitivecomputations Dolphin3.0 R1 Mistral 24B needs ~20.8 GB VRAM. Intel Arc Pro B60 24GB has 24.0 GB. With Q4_K_M quantization, expect ~17 tok/s.
Runtime: llama.cppCapacity: TightBandwidth: MediumStack: StandardBottleneck: 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.
Select quantization to explore
Q4_K_M (Medium quality) — 20.8 GB, 16.8 tok/s, Tight fit
20.8 GB required24.0 GB available
87% VRAM used
Fit status
Tight fit
Decode
16.8 tok/s
TTFT
11510 ms
Safe context
34K
Memory
20.8 GB / 24.0 GB
Memory breakdown
Weights14.6 GB
KV Cache2.8 GB
Runtime0.9 GB
Headroom2.4 GB
See how fast it feels
See how fast it feelscognitivecomputations Dolphin3.0 R1 Mistral 24B on Intel Arc Pro B60 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: 16.8 tok/s decode · 11.5s TTFT (warm) · 42 tok/s prefill
What limits this setup
The raw memory story may look fine, but the software ecosystem is still a constraint here.
Runtime ecosystem is narrower than CUDA
Intel GPUs can look attractive on memory per dollar, but local AI tooling, kernels, and model coverage are still broader and easier on CUDA today.
Best improvement path
Prefer CUDA if you want the path of least resistance
If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Runs well | 16.8 tok/s | 6278 ms | 34K |
| Coding | C | Tight fit | 16.8 tok/s | 11510 ms | 34K |
| Agentic Coding | C | Runs with offload | 16.8 tok/s | 16742 ms | 34K |
| Reasoning | C | Tight fit | 16.8 tok/s | 13603 ms | 34K |
| RAG | C | Runs with offload | 16.8 tok/s | 20928 ms | 34K |
Quantization options
How cognitivecomputations Dolphin3.0 R1 Mistral 24B (24B params) fits at each quantization level on Intel Arc Pro B60 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 startUpgrade options
Hardware that runs cognitivecomputations Dolphin3.0 R1 Mistral 24B well
32 GB VRAM (+8)1792 GB/s (+1336)
B
Raises estimated decode speed by about 290%.65.5 tok/s decode
Raises estimated decode speed by about 290%.
Adds memory headroom for longer context windows and future model growth.
This is not only a hardware jump. It also gives you a cleaner runtime ecosystem for local LLM tooling.
~$1,999 MSRP