Ministral 3 8B needs ~10.8 GB VRAM. MacBook Pro M3 Pro 18GB has 13.0 GB. With Q4_K_M quantization, expect ~24 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
Tight fit
Decode
24.1 tok/s
TTFT
8026 ms
Safe context
32K
Memory
10.8 GB / 13.0 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 | A | Runs well | 24.1 tok/s | 4378 ms | 32K |
| Coding | A | Tight fit | 24.1 tok/s | 8026 ms | 32K |
| Agentic Coding | A | Runs with offload (needs ~0 GB host RAM) | 21.9 tok/s | 12884 ms | 32K |
| Reasoning | A | Tight fit | 24.1 tok/s | 9485 ms | 32K |
| RAG | A | Runs with offload (needs ~0 GB host RAM) | 21.9 tok/s | 16106 ms | 32K |
How Ministral 3 8B (8B params) fits at each quantization level on MacBook Pro M3 Pro 18GB (13.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.1 GB | Low | A79 |
Q3_K_S | 3 | 3.9 GB | Low | A80 |
NVFP4 | 4 | 4.5 GB | Medium | A81 |
Q4_K_M | 4 | 4.9 GB | Medium | A81 |
Q5_K_M | 5 | 5.8 GB | High | A83 |
Q6_K | 6 | 6.6 GB | High | A83 |
Q8_0Best for your GPU | 8 | 8.6 GB | Very High | A82 |
F16 | 16 | 16.4 GB | Maximum | F0 |
Copy-paste commands to run Ministral 3 8B on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "mistralai/Ministral-3-8B-Instruct-2512" \
--hf-file "Ministral-3-8B-Instruct-2512-Q4_K_M.gguf" \
-c 4096 -ngl 99Your hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
 Qwen 3.5 9B | 9B | S | 21.4 tok/s | |
| Qwen 3 14B | 14B | A | 10.6 tok/s | |
 Ministral 3 14B | 14B | A | 10.5 tok/s | |
 Phi-4 14B | 14B | B | 9.9 tok/s | |
| Qwen 2.5 14B | 14B | B | 10.1 tok/s |
Yes, MacBook Pro M3 Pro 18GB can run Ministral 3 8B with a A grade (Tight fit). Expected decode speed: 24.1 tok/s.
Ministral 3 8B (8B parameters) requires approximately 10.8 GB of memory with Q4_K_M quantization.
The recommended quantization for Ministral 3 8B is Q4_K_M, which balances quality and memory efficiency.
On MacBook Pro M3 Pro 18GB, Ministral 3 8B achieves approximately 24.1 tokens per second decode speed with a time-to-first-token of 8026ms using Q4_K_M quantization.
For coding workloads, Ministral 3 8B on MacBook Pro M3 Pro 18GB receives a A grade with 24.1 tok/s and 32K context.
On MacBook Pro M3 Pro 18GB, Ministral 3 8B can safely use up to 32K tokens of context. The model's official context limit is 262K, but available memory constrains the safe maximum.
Not always. MacBook Pro M3 Pro 18GB 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/ministral-3-8b-on-m3-pro-18gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: