 |
VOOZH | about |
starcoder2 15b i1 needs ~13.5 GB VRAM. MacBook Pro M4 16GB has 11.5 GB. With Q4_K_M quantization, expect ~7 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
2.0 GB over capacity — needs offload or smaller quantization
Fit status
Very compromised (needs ~1.4 GB host RAM)
Decode
6.8 tok/s
TTFT
28373 ms
Safe context
4K
Memory
13.5 GB / 11.5 GB
Offload
10%
It fits through host-memory offload, and offload is the main reason performance drops.
CPU or host-memory offload is active
About 10% 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.
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.
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 1.4 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 ~0.8 GB host RAM) | 7.5 tok/s | 14163 ms | 4K |
| Coding | D | Very compromised (needs ~1.4 GB host RAM) | 6.8 tok/s | 28373 ms | 4K |
| Agentic Coding | F | Too heavy | 6.4 tok/s | 44275 ms | 4K |
| Reasoning | D | Very compromised (needs ~1.4 GB host RAM) | 6.8 tok/s | 33532 ms | 4K |
| RAG | F | Too heavy | 5.9 tok/s | 59896 ms |
How starcoder2 15b i1 (15B params) fits at each quantization level on MacBook Pro M4 16GB (11.5 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.9 GB | Low | C52 |
Q3_K_S | 3 | 7.4 GB | Low | C51 |
NVFP4Best for your GPU |
Copy-paste commands to run starcoder2 15b i1 on your machine.
Run
lms load hf-mradermacher--starcoder2-15b-i1-gguf && lms server startUpgrade options
Removes host-memory offload, which is usually the single biggest latency and throughput win.
Raises estimated decode speed by about 28%.
~$799 MSRP
Removes host-memory offload, which is usually the single biggest latency and throughput win.
Raises estimated decode speed by about 28%.
~$1,099 MSRP
Removes host-memory offload, which is usually the single biggest latency and throughput win.
Raises estimated decode speed by about 28%.
~$1,099 MSRP
Removes host-memory offload, which is usually the single biggest latency and throughput win.
Raises estimated decode speed by about 703%.
~$2,000 MSRP
| 4K |
| 4 |
8.4 GB |
| Medium |
| C51 |
Q4_K_M | 4 | 9.2 GB | Medium | F0 |
Q5_K_M | 5 | 10.8 GB | High | F0 |
Q6_K | 6 | 12.3 GB | High | F0 |
Q8_0 | 8 | 16.1 GB | Very High | F0 |
F16 | 16 | 30.7 GB | Maximum | F0 |
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.
