Mac Studio M3 Ultra 96GBBudget pick
96 GB Unified (+48)819 GB/s (+147)
C
Adds memory headroom for longer context windows and future model growth.101.4 tok/s decode
Adds memory headroom for longer context windows and future model growth.
~$3,999 MSRP
Can Yi Coder 9B Chat run on Quadro RTX 8000 48GB?
YES — Runs Great
C47Usable
○Estimated from fit model
Yi Coder 9B Chat needs ~12.5 GB VRAM. Quadro RTX 8000 48GB has 48.0 GB. With Q4_K_M quantization, expect ~85 tok/s.
Runtime: OllamaCapacity: RoomyBandwidth: MediumStack: 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) — 12.5 GB, 84.5 tok/s, Runs well
12.5 GB required48.0 GB available
26% VRAM used
Fit status
Runs well
Decode
84.5 tok/s
TTFT
2292 ms
Safe context
554K
Memory
12.5 GB / 48.0 GB
Memory breakdown
Weights5.5 GB
KV Cache1.1 GB
Runtime1.2 GB
Headroom4.8 GB
See how fast it feels
See how fast it feelsYi Coder 9B Chat on Quadro RTX 8000 48GB
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: 84.5 tok/s decode · 2.3s TTFT (warm) · 211 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 | C | Runs well | 84.5 tok/s | 1250 ms | 554K |
| Coding | C | Runs well | 84.5 tok/s | 2292 ms | 554K |
| Agentic Coding | C | Runs well | 84.5 tok/s | 3334 ms | 554K |
| Reasoning | C | Runs well | 84.5 tok/s | 2709 ms | 554K |
| RAG | C | Runs well | 84.5 tok/s | 4168 ms | 554K |
Quantization options
How Yi Coder 9B Chat (9B params) fits at each quantization level on Quadro RTX 8000 48GB (48.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.5 GB | Low | C42 |
Q3_K_S | 3 | 4.4 GB | Low | C42 |
NVFP4 | 4 | 5.0 GB | Medium | C42 |
Q4_K_M | 4 | 5.5 GB | Medium | C42 |
Q5_K_M | 5 | 6.5 GB | High | C42 |
Q6_K | 6 | 7.4 GB | High | C42 |
Q8_0 | 8 | 9.6 GB | Very High | C43 |
F16Best for your GPU | 16 | 18.5 GB | Maximum | C45 |
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