cognitivecomputations Dolphin3.0 R1 Mistral 24B needs ~28.7 GB VRAM. MacBook Pro M2 Max 96GB has 69.1 GB. With Q4_K_M quantization, expect ~16 tok/s.
Operating mode
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
Fit status
Runs well
Decode
15.8 tok/s
TTFT
12217 ms
Safe context
246K
Memory
28.7 GB / 69.1 GB
This setup is broadly balanced for this model.
Shared-memory contention still exists
The OS, browser, and inference runtime all compete for the same physical memory pool, so real-world headroom is less forgiving than raw capacity suggests.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Runs well | 15.8 tok/s | 6664 ms | 246K |
| Coding | C | Runs well | 15.8 tok/s | 12217 ms | 246K |
| Agentic Coding | C | Runs well | 15.8 tok/s | 17770 ms | 246K |
| Reasoning | C | Runs well | 15.8 tok/s | 14438 ms | 246K |
| RAG | C | Runs well | 15.8 tok/s | 22212 ms | 246K |
Inference speed
Estimated decode speed (tokens/sec) for cognitivecomputations Dolphin3.0 R1 Mistral 24B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~82 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.
| GPU / Mac | Memory | Quant | Speed (tok/s) | Fits? |
|---|---|---|---|---|
 RTX 5090 32GB | 32 GB | Q4_K_M | 82.0 | Fits |
| RTX 4090 24GB | 24 GB | Q4_K_M | 52.3 | Tight |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 47.2 | Tight |
| RTX 3090 24GB | 24 GB | Q4_K_M | 44.8 | Tight |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 38.0 | Fits |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 34.2 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 34.2 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 31.7 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 30.1 | Fits |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 21.5 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 19.1 | Too big |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 16.4 | Fits |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 15.0 | Fits |
| RTX 4070 12GB | 12 GB | Q4_K_M | 6.7 | Too big |
| RTX 3060 12GB | 12 GB | Q4_K_M | 4.2 | Too big |
| RTX 4060 8GB | 8 GB | Q4_K_M | 2.0 | Too big |
Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.
How cognitivecomputations Dolphin3.0 R1 Mistral 24B (24B params) fits at each quantization level on MacBook Pro M2 Max 96GB (69.1 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 9.4 GB | Low | C41 |
Q3_K_S | 3 | 11.8 GB | Low | C41 |
NVFP4 | 4 | 13.4 GB | Medium | C41 |
Q4_K_M | 4 | 14.6 GB | Medium | C42 |
Q5_K_M | 5 | 17.3 GB | High | C42 |
Q6_K | 6 | 19.7 GB | High | C43 |
Q8_0 | 8 | 25.7 GB | Very High | C44 |
F16Best for your GPU | 16 | 49.2 GB | Maximum | C48 |
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-Optionen
Raises estimated decode speed by about 101%.
Adds memory headroom for longer context windows and future model growth.
ca. $3,999 MSRP
Raises estimated decode speed by about 91%.
Adds memory headroom for longer context windows and future model growth.
ca. $3,999 MSRP
Raises estimated decode speed by about 116%.
Adds memory headroom for longer context windows and future model growth.
ca. $4,999 MSRP
Yes, MacBook Pro M2 Max 96GB can run cognitivecomputations Dolphin3.0 R1 Mistral 24B with a C grade (Runs well). Expected decode speed: 15.8 tok/s.
cognitivecomputations Dolphin3.0 R1 Mistral 24B (24B parameters) requires approximately 28.7 GB of memory with Q4_K_M quantization.
The recommended quantization for cognitivecomputations Dolphin3.0 R1 Mistral 24B is Q4_K_M, which balances quality and memory efficiency.
On MacBook Pro M2 Max 96GB, cognitivecomputations Dolphin3.0 R1 Mistral 24B achieves approximately 15.8 tokens per second decode speed with a time-to-first-token of 12217ms using Q4_K_M quantization.
For coding workloads, cognitivecomputations Dolphin3.0 R1 Mistral 24B on MacBook Pro M2 Max 96GB receives a C grade with 15.8 tok/s and 246K context.
On MacBook Pro M2 Max 96GB, cognitivecomputations Dolphin3.0 R1 Mistral 24B can safely use up to 246K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.
Not always. MacBook Pro M2 Max 96GB can often fit larger models thanks to unified memory, but a discrete GPU with dedicated high-bandwidth VRAM may still decode faster once the model fits. For this combination, the important distinction is capacity versus sustained throughput.
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-m2-max-96gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: