456 GB/s (+256)
C
Raises estimated decode speed by about 56%.39.9 tok/s decode
Raises estimated decode speed by about 56%.
~$249 MSRP
Can Yi 9B Coder i1 run on MacBook Pro M2 Pro 16GB?
YES — Runs Great
C52Usable
○Estimated from fit model
Yi 9B Coder i1 needs ~9.2 GB VRAM. MacBook Pro M2 Pro 16GB has 11.5 GB. With Q4_K_M quantization, expect ~26 tok/s.
Runtime: llama.cppCapacity: RoomyBandwidth: Very lowStack: StandardBottleneck: Memory bandwidth
Share:
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) — 9.2 GB, 25.5 tok/s, Runs well
9.2 GB required11.5 GB available
80% VRAM used
Fit status
Runs well
Decode
25.5 tok/s
TTFT
7592 ms
Safe context
52K
Memory
9.2 GB / 11.5 GB
Memory breakdown
Weights5.5 GB
KV Cache1.1 GB
Runtime0.9 GB
Headroom1.7 GB
See how fast it feels
See how fast it feelsYi 9B Coder i1 on MacBook Pro M2 Pro 16GB
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: 25.5 tok/s decode · 7.6s TTFT (warm) · 64 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 | 25.5 tok/s | 4141 ms | 52K |
| Coding | C | Runs well | 25.5 tok/s | 7592 ms | 52K |
| Agentic Coding | C | Tight fit | 25.5 tok/s | 11043 ms | 52K |
| Reasoning | C | Runs well | 25.5 tok/s | 8972 ms | 52K |
| RAG | C | Tight fit | 25.5 tok/s | 13803 ms | 52K |
Quantization options
How Yi 9B Coder i1 (9B params) fits at each quantization level on MacBook Pro M2 Pro 16GB (11.5 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.5 GB | Low | C50 |
Q3_K_S | 3 | 4.4 GB | Low | C51 |
NVFP4 | 4 | 5.0 GB | Medium | C52 |
Q4_K_M | 4 | 5.5 GB | Medium | C52 |
Q5_K_M | 5 | 6.5 GB | High | C52 |
Q6_KBest for your GPU | 6 | 7.4 GB | High | C52 |
Q8_0 | 8 | 9.6 GB | Very High | F0 |
F16 | 16 | 18.5 GB | Maximum | F0 |
Get started
Copy-paste commands to run Yi 9B Coder i1 on your machine.
Run
lms load hf-mradermacher--yi-9b-coder-i1-gguf && lms server startUpgrade options
