RTX PRO 6000 Blackwell Workstation Edition 96GBOpção econômica1792 GB/s (+992)
C
Raises estimated decode speed by about 242%.164.5 tok/s decodificação
Raises estimated decode speed by about 242%.
~$9,999 MSRP
Can StarCoder2 15B run on Mac Studio M1 Ultra 128GB?
YES — Runs Great
C46Usable
Estimated from fit model
StarCoder2 15B needs ~25.6 GB VRAM. Mac Studio M1 Ultra 128GB has 92.2 GB. With Q4_K_M quantization, expect ~48 tok/s.
Runtime: llama.cppCapacity: RoomyBandwidth: HighStack: StandardBottleneck: Balanced
Operating mode
Choose the run profile you care about
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
Q4_K_M (Medium quality) — 25.6 GB, 48.1 tok/s, Runs well
25.6 GB required92.2 GB available
28% VRAM used
Fit status
Runs well
Decode
48.1 tok/s
TTFT
4026 ms
Safe context
622K
Memory
25.6 GB / 92.2 GB
Memory breakdown
Weights9.2 GB
KV Cache1.8 GB
Runtime0.9 GB
Headroom13.8 GB
See how fast it feels
See how fast it feelsStarCoder2 15B on Mac Studio M1 Ultra 128GB
1st promptCold start — includes initialization
>Write a Python function to sort a list
Here's a Python function that sorts a list using quicksort:
def quicksort(arr):
if len(arr) <= 1:
return arr
pivot = arr[len(arr) // 2]
left = [x for x in arr if x < pivot]
middle = [x for x in arr if x == pivot]
right = [x for x in arr if x > pivot]
return quicksort(left) + middle + quicksort(right)
# Example usage
numbers = [3, 6, 8, 10, 1, 2, 1]
print(quicksort(numbers)) # [1, 1, 2, 3, 6, 8, 10]
The algorithm picks a pivot, partitions the list into smaller, equal, and larger elements, then recursively sorts each partition and concatenates the results.
2nd promptWarm — model ready, no init overhead
>Now add type hints and a docstring
def quicksort(arr: list[int]) -> list[int]:
"""Sort a list using the quicksort algorithm.
Args:
arr: List of integers to sort.
Returns:
A new sorted list.
"""
if len(arr) <= 1:
return arr
pivot = arr[len(arr) // 2]
left = [x for x in arr if x < pivot]
middle = [x for x in arr if x == pivot]
right = [x for x in arr if x > pivot]
return quicksort(left) + middle + quicksort(right)
Added type hints for the input and return type, plus a Google-style docstring.
Estimated: 48.1 tok/s decode · 4.0s TTFT (warm) · 120 tok/s prefill
What limits this setup
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.
Best improvement path
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Runs well | 48.1 tok/s | 2196 ms | 622K |
| Coding | C | Runs well | 48.1 tok/s | 4026 ms | 622K |
| Agentic Coding | C | Runs well | 48.1 tok/s | 5856 ms | 622K |
| Reasoning | C | Runs well | 48.1 tok/s | 4758 ms | 622K |
| RAG | C | Runs well | 48.1 tok/s | 7320 ms | 622K |
Quantization options
How StarCoder2 15B (15B params) fits at each quantization level on Mac Studio M1 Ultra 128GB (92.2 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.9 GB | Low | D39 |
Q3_K_S | 3 | 7.4 GB | Low | D39 |
NVFP4 | 4 | 8.4 GB | Medium | D39 |
Q4_K_M | 4 | 9.2 GB | Medium | D39 |
Q5_K_M | 5 | 10.8 GB | High | D40 |
Q6_K | 6 | 12.3 GB | High | D40 |
Q8_0 | 8 | 16.1 GB | Very High | C40 |
F16Best for your GPU | 16 | 30.7 GB | Maximum | C42 |
Get started
Copy-paste commands to run StarCoder2 15B on your machine.
Run
lms load hf-second-state--starcoder2-15b-gguf && lms server startOpções de upgrade
Hardware que roda bem StarCoder2 15B
Frequently asked questions
Can Mac Studio M1 Ultra 128GB run StarCoder2 15B?
Yes, Mac Studio M1 Ultra 128GB can run StarCoder2 15B with a C grade (Runs well). Expected decode speed: 48.1 tok/s.
How much VRAM does StarCoder2 15B need?
StarCoder2 15B (15B parameters) requires approximately 25.6 GB of memory with Q4_K_M quantization.
What is the best quantization for StarCoder2 15B?
The recommended quantization for StarCoder2 15B is Q4_K_M, which balances quality and memory efficiency.
What speed will StarCoder2 15B run at on Mac Studio M1 Ultra 128GB?
On Mac Studio M1 Ultra 128GB, StarCoder2 15B achieves approximately 48.1 tokens per second decode speed with a time-to-first-token of 4026ms using Q4_K_M quantization.
Can Mac Studio M1 Ultra 128GB run StarCoder2 15B for coding?
For coding workloads, StarCoder2 15B on Mac Studio M1 Ultra 128GB receives a C grade with 48.1 tok/s and 622K context.
What context window can StarCoder2 15B use on Mac Studio M1 Ultra 128GB?
On Mac Studio M1 Ultra 128GB, StarCoder2 15B can safely use up to 622K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.
Is unified memory on Mac Studio M1 Ultra 128GB as fast as VRAM for StarCoder2 15B?
Not always. Mac Studio M1 Ultra 128GB 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.
Embed this result▼
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/hf-second-state--starcoder2-15b-gguf-on-m1-ultra-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: