Intel Arc B580 12GBBudget pick456 GB/s (+256)
C
Raises estimated decode speed by about 56%.44.9 tok/s decode
Raises estimated decode speed by about 56%.
~$249 MSRP
dolphin 2.9.4 llama3.1 8b needs ~8.4 GB VRAM. MacBook Pro M2 Pro 16GB has 11.5 GB. With Q4_K_M quantization, expect ~29 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
28.7 tok/s
TTFT
6748 ms
Safe context
68K
Memory
8.4 GB / 11.5 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 | 28.7 tok/s | 3681 ms | 68K |
| Coding | C | Runs well | 28.7 tok/s | 6748 ms | 68K |
| Agentic Coding | C | Runs well | 28.7 tok/s | 9816 ms | 68K |
| Reasoning | C | Runs well | 28.7 tok/s | 7975 ms | 68K |
| RAG | C | Runs well | 28.7 tok/s | 12270 ms | 68K |
Inference speed
Estimated decode speed (tokens/sec) for dolphin 2.9.4 llama3.1 8b at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~112 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 | 112.0 | Fits |
| RTX 4090 24GB | 24 GB | Q4_K_M | 112.0 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 112.0 | Fits |
| RTX 3090 24GB | 24 GB | Q4_K_M | 112.0 | Fits |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 112.0 | Fits |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 112.0 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 95.1 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 90.2 | Fits |
| RTX 4070 12GB | 12 GB | Q4_K_M | 77.5 | Fits |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 76.8 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 76.8 | Fits |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 49.2 | Fits |
| RTX 3060 12GB | 12 GB | Q4_K_M | 48.7 | Fits |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 45.1 | Fits |
| RTX 4060 8GB | 8 GB | Q4_K_M | 40.7 | Offloads |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 39.6 | Fits |
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 dolphin 2.9.4 llama3.1 8b (8B params) fits at each quantization level on MacBook Pro M2 Pro 16GB (11.5 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.1 GB | Low | C50 |
Q3_K_S | 3 | 3.9 GB | Low | C51 |
NVFP4 | 4 | 4.5 GB | Medium | C52 |
Q4_K_M | 4 | 4.9 GB | Medium | C52 |
Q5_K_M | 5 | 5.8 GB | High | C52 |
Q6_KBest for your GPU | 6 | 6.6 GB | High | C52 |
Q8_0 | 8 | 8.6 GB | Very High | F0 |
F16 | 16 | 16.4 GB | Maximum | F0 |
Copy-paste commands to run dolphin 2.9.4 llama3.1 8b on your machine.
Run
lms load hf-bartowski--dolphin-2-9-4-llama3-1-8b-gguf && lms server startUpgrade options
Intel Arc B580 12GBBudget pickRaises estimated decode speed by about 56%.
~$249 MSRP
RTX 3060 12GBBest valueRaises estimated decode speed by about 43%.
~$329 MSRP
Yes, MacBook Pro M2 Pro 16GB can run dolphin 2.9.4 llama3.1 8b with a C grade (Runs well). Expected decode speed: 28.7 tok/s.
dolphin 2.9.4 llama3.1 8b (8B parameters) requires approximately 8.4 GB of memory with Q4_K_M quantization.
The recommended quantization for dolphin 2.9.4 llama3.1 8b is Q4_K_M, which balances quality and memory efficiency.
On MacBook Pro M2 Pro 16GB, dolphin 2.9.4 llama3.1 8b achieves approximately 28.7 tokens per second decode speed with a time-to-first-token of 6748ms using Q4_K_M quantization.
For coding workloads, dolphin 2.9.4 llama3.1 8b on MacBook Pro M2 Pro 16GB receives a C grade with 28.7 tok/s and 68K context.
On MacBook Pro M2 Pro 16GB, dolphin 2.9.4 llama3.1 8b can safely use up to 68K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.
Not always. MacBook Pro M2 Pro 16GB 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--dolphin-2-9-4-llama3-1-8b-gguf-on-m2-pro-16gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: