cognitivecomputations Dolphin3.0 R1 Mistral 24B needs ~19.1 GB VRAM. RTX 4070 Ti Super 16GB has 16.0 GB. With NVFP4 quantization, expect ~22 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
4.3 GB over capacity — needs offload or smaller quantization
Fit status
Too heavy
Decode
16.8 tok/s
TTFT
11545 ms
Safe context
4K
Memory
20.3 GB / 16.0 GB
Offload
20%
It fits through host-memory offload, and offload is the main reason performance drops.
CPU or host-memory offload is active
About 20% of the working set spills out of accelerator memory, which usually hurts latency and sustained decode throughput.
Very little memory headroom
You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.
Remove offload with more accelerator memory
Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Increase host RAM if you keep offloading
This setup may need roughly 2.2 GB of extra host RAM just for the offloaded portion, before OS and other tools.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | D | Very compromised (needs ~2.2 GB host RAM) | 19.5 tok/s | 5412 ms | 4K |
| Coding | F | Too heavy | 16.8 tok/s | 11545 ms | 4K |
| Agentic Coding | F | Too heavy | 12.8 tok/s | 22080 ms | 4K |
| Reasoning | F | Too heavy | 16.8 tok/s | 13644 ms | 4K |
| RAG | F | Too heavy | 12.8 tok/s | 27600 ms | 4K |
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 RTX 4070 Ti Super 16GB (16.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 9.4 GB | Low | C51 |
Q3_K_SBest for your GPU | 3 | 11.8 GB | Low | C51 |
NVFP4 | 4 | 13.4 GB | Medium | F0 |
Q4_K_M | 4 | 14.6 GB | Medium | F0 |
Q5_K_M | 5 | 17.3 GB | High | F0 |
Q6_K | 6 | 19.7 GB | High | F0 |
Q8_0 | 8 | 25.7 GB | Very High | F0 |
F16 | 16 | 49.2 GB | Maximum | F0 |
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 startOpções de upgrade
RTX 4000 Ada 20GBOpção econômicaMakes the model fit on the accelerator instead of staying completely out of reach.
Removes host-memory offload, which is usually the single biggest latency and throughput win.
~$1,250 MSRP
RTX 3090 24GBMelhor custo-benefícioMakes the model fit on the accelerator instead of staying completely out of reach.
Removes host-memory offload, which is usually the single biggest latency and throughput win.
~$1,499 MSRP
RTX 4090 24GBUpgrade NVIDIAMakes the model fit on the accelerator instead of staying completely out of reach.
Removes host-memory offload, which is usually the single biggest latency and throughput win.
~$1,599 MSRP
Yes, RTX 4070 Ti Super 16GB can run cognitivecomputations Dolphin3.0 R1 Mistral 24B at NVFP4 quantization (Very compromised (needs ~2.2 GB host RAM)). The recommended Q4_K_M requires 20.3 GB which exceeds available memory, but at NVFP4 it needs only 19.1 GB. Expected decode speed: 21.8 tok/s.
cognitivecomputations Dolphin3.0 R1 Mistral 24B (24B parameters) requires approximately 20.3 GB at Q4_K_M quantization. On RTX 4070 Ti Super 16GB, it fits at NVFP4 using 19.1 GB.
The recommended quantization is Q4_K_M, but on RTX 4070 Ti Super 16GB the best fitting quantization is NVFP4, which uses 19.1 GB.
On RTX 4070 Ti Super 16GB, cognitivecomputations Dolphin3.0 R1 Mistral 24B achieves approximately 21.8 tokens per second decode speed with a time-to-first-token of 8876ms using NVFP4 quantization.
For coding workloads, cognitivecomputations Dolphin3.0 R1 Mistral 24B on RTX 4070 Ti Super 16GB receives a F grade with 16.8 tok/s and 4K context.
On RTX 4070 Ti Super 16GB, cognitivecomputations Dolphin3.0 R1 Mistral 24B can safely use up to 4K tokens of context at NVFP4 quantization. The model's official context limit is —, but available memory constrains the safe maximum.
Remove offload with more accelerator memory. Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.
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-rtx-4070-ti-super-16gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: