Mac Studio M3 Ultra 96GB经济之选
96 GB Unified (+48)
C
Adds memory headroom for longer context windows and future model growth.101.4 tok/s 解码
Adds memory headroom for longer context windows and future model growth.
~$3,999 MSRP
Can Yi 9B Coder i1 run on NVIDIA L20 48GB?
YES — Runs Great
C47Usable
Estimated from fit model
Yi 9B Coder i1 needs ~12.5 GB VRAM. NVIDIA L20 48GB has 48.0 GB. With Q4_K_M quantization, expect ~115 tok/s.
Runtime: OllamaCapacity: RoomyBandwidth: HighStack: BasicBottleneck: 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) — 12.5 GB, 114.9 tok/s, Runs well
12.5 GB required48.0 GB available
26% VRAM used
Fit status
Runs well
Decode
114.9 tok/s
TTFT
1685 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 9B Coder i1 on NVIDIA L20 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: 114.9 tok/s decode · 1.7s TTFT (warm) · 287 tok/s prefill
What limits this setup
This setup is broadly balanced for this model.
No major red flags
This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.
Best improvement path
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Runs well | 114.9 tok/s | 919 ms | 554K |
| Coding | C | Runs well | 114.9 tok/s | 1685 ms | 554K |
| Agentic Coding | C | Runs well | 114.9 tok/s | 2451 ms | 554K |
| Reasoning | C | Runs well | 114.9 tok/s | 1992 ms | 554K |
| RAG | C | Runs well | 114.9 tok/s | 3064 ms | 554K |
Quantization options
How Yi 9B Coder i1 (9B params) fits at each quantization level on NVIDIA L20 48GB (48.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.5 GB | Low | C41 |
Q3_K_S | 3 | 4.4 GB | Low | C41 |
NVFP4 | 4 | 5.0 GB | Medium | C41 |
Q4_K_M | 4 | 5.5 GB | Medium | C41 |
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 | C42 |
F16Best for your GPU | 16 | 18.5 GB | Maximum | C45 |
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 start升级选项
能流畅运行 Yi 9B Coder i1 的硬件
Frequently asked questions
Can NVIDIA L20 48GB run Yi 9B Coder i1?
Yes, NVIDIA L20 48GB can run Yi 9B Coder i1 with a C grade (Runs well). Expected decode speed: 114.9 tok/s.
How much VRAM does Yi 9B Coder i1 need?
Yi 9B Coder i1 (9B parameters) requires approximately 12.5 GB of memory with Q4_K_M quantization.
What is the best quantization for Yi 9B Coder i1?
The recommended quantization for Yi 9B Coder i1 is Q4_K_M, which balances quality and memory efficiency.
What speed will Yi 9B Coder i1 run at on NVIDIA L20 48GB?
On NVIDIA L20 48GB, Yi 9B Coder i1 achieves approximately 114.9 tokens per second decode speed with a time-to-first-token of 1685ms using Q4_K_M quantization.
Can NVIDIA L20 48GB run Yi 9B Coder i1 for coding?
For coding workloads, Yi 9B Coder i1 on NVIDIA L20 48GB receives a C grade with 114.9 tok/s and 554K context.
What context window can Yi 9B Coder i1 use on NVIDIA L20 48GB?
On NVIDIA L20 48GB, Yi 9B Coder i1 can safely use up to 554K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.
Embed this result▼
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/hf-mradermacher--yi-9b-coder-i1-gguf-on-l20-48gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: