RX 7900 XTX 24GBBudget pick
960 GB/s (+560)
C
Raises estimated decode speed by about 198%.125.9 tok/s decode
Raises estimated decode speed by about 198%.
~$999 MSRP
Can Yi Coder 9B Chat run on MacBook Pro M2 Max 32GB?
YES — Runs Great
C50Usable
○Estimated from fit model
Yi Coder 9B Chat needs ~10.9 GB VRAM. MacBook Pro M2 Max 32GB has 23.0 GB. With Q4_K_M quantization, expect ~42 tok/s.
Runtime: llama.cppCapacity: RoomyBandwidth: LowStack: StandardBottleneck: Balanced
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) — 10.9 GB, 42.3 tok/s, Runs well
10.9 GB required23.0 GB available
47% VRAM used
Fit status
Runs well
Decode
42.3 tok/s
TTFT
4581 ms
Safe context
200K
Memory
10.9 GB / 23.0 GB
Memory breakdown
Weights5.5 GB
KV Cache1.1 GB
Runtime0.9 GB
Headroom3.5 GB
See how fast it feels
See how fast it feelsYi Coder 9B Chat on MacBook Pro M2 Max 32GB
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: 42.3 tok/s decode · 4.6s TTFT (warm) · 106 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 | 42.3 tok/s | 2499 ms | 200K |
| Coding | C | Runs well | 42.3 tok/s | 4581 ms | 200K |
| Agentic Coding | C | Runs well | 42.3 tok/s | 6664 ms | 200K |
| Reasoning | C | Runs well | 42.3 tok/s | 5414 ms | 200K |
| RAG | C | Runs well | 42.3 tok/s | 8330 ms | 200K |
Quantization options
How Yi Coder 9B Chat (9B params) fits at each quantization level on MacBook Pro M2 Max 32GB (23.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.5 GB | Low | C45 |
Q3_K_S | 3 | 4.4 GB | Low | C45 |
NVFP4 | 4 | 5.0 GB | Medium | C46 |
Q4_K_M | 4 | 5.5 GB | Medium | C46 |
Q5_K_M | 5 | 6.5 GB | High | C47 |
Q6_K | 6 | 7.4 GB | High | C47 |
Q8_0 | 8 | 9.6 GB | Very High | C49 |
F16Best for your GPU | 16 | 18.5 GB | Maximum | C50 |
Get started
Copy-paste commands to run Yi Coder 9B Chat on your machine.
Run
lms load hf-maziyarpanahi--yi-coder-9b-chat-gguf && lms server startUpgrade options
