32 GB VRAM (+8)1792 GB/s (+1446)
B
Raises estimated decode speed by about 212%.126 tok/s decode
Raises estimated decode speed by about 212%.
Adds memory headroom for longer context windows and future model growth.
~$1,999 MSRP
Can Yi Coder 9B run on Tesla P40 24GB?
YES — Runs Great
B61Good
○Estimated from fit model
Yi Coder 9B needs ~10.6 GB VRAM. Tesla P40 24GB has 24.0 GB. With Q4_K_M quantization, expect ~37 tok/s.
Runtime: OllamaCapacity: RoomyBandwidth: LowStack: BasicBottleneck: 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) — 10.6 GB, 40.4 tok/s, Runs well
10.6 GB required24.0 GB available
44% VRAM used
Fit status
Runs well
Decode
40.4 tok/s
TTFT
4788 ms
Safe context
131K
Memory
10.6 GB / 24.0 GB
Memory breakdown
Weights5.5 GB
KV Cache1.5 GB
Runtime1.2 GB
Headroom2.4 GB
See how fast it feels
See how fast it feelsYi Coder 9B on Tesla P40 24GB
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: 40.4 tok/s decode · 4.8s TTFT (warm) · 101 tok/s prefill
What limits this setup
This setup is broadly balanced for this model.
Older PCIe generation
PCIe 3.0 is workable, but it compounds the penalty when you offload heavily or try to scale across multiple cards.
Best improvement path
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | B | Runs well | 37.2 tok/s | 2840 ms | 131K |
| Coding | B | Runs well | 37.2 tok/s | 5207 ms | 131K |
| Agentic Coding | B | Runs well | 37.2 tok/s | 7573 ms | 131K |
| Reasoning | B | Runs well | 37.2 tok/s | 6153 ms | 131K |
| RAG | B | Runs well | 37.2 tok/s | 9466 ms | 131K |
Quantization options
How Yi Coder 9B (9B params) fits at each quantization level on Tesla P40 24GB (24.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.5 GB | Low | B57 |
Q3_K_S | 3 | 4.4 GB | Low | B57 |
NVFP4 | 4 |
Get started
Copy-paste commands to run Yi Coder 9B on your machine.
Run
lms load Yi-Coder-9B-Chat && lms server startUpgrade options
Hardware that runs Yi Coder 9B well
32 GB VRAM (+8)896 GB/s (+550)
B
Raises estimated decode speed by about 212%.126 tok/s decode
Raises estimated decode speed by about 212%.
Adds memory headroom for longer context windows and future model growth.
~$2,499 MSRP
32 GB VRAM (+8)576 GB/s (+230)
B
Raises estimated decode speed by about 126%.91.3 tok/s decode
Raises estimated decode speed by about 126%.
Adds memory headroom for longer context windows and future model growth.
~$4,000 MSRP