MacBook Pro M4 Max 96GBコスパ重視
96 GB Unified (+48)
C
Adds memory headroom for longer context windows and future model growth.21 tok/sデコード
Adds memory headroom for longer context windows and future model growth.
〜$2,499 MSRP
Can Yi Coder 1.5B Chat run on NVIDIA L40S 48GB?
YES — Runs Great
C41Usable
Estimated from fit model
Yi Coder 1.5B Chat needs ~6.8 GB VRAM. NVIDIA L40S 48GB has 48.0 GB. With Q4_K_M quantization, expect ~24 tok/s.
Runtime: llama.cppCapacity: RoomyBandwidth: HighStack: StandardBottleneck: 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) — 6.8 GB, 24.0 tok/s, Runs well
6.8 GB required48.0 GB available
14% VRAM used
Fit status
Runs well
Decode
24.0 tok/s
TTFT
8067 ms
Safe context
3.8M
Memory
6.8 GB / 48.0 GB
Memory breakdown
Weights0.9 GB
KV Cache0.2 GB
Runtime0.9 GB
Headroom4.8 GB
See how fast it feels
See how fast it feelsYi Coder 1.5B Chat on NVIDIA L40S 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: 24.0 tok/s decode · 8.1s TTFT (warm) · 60 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 | 24.0 tok/s | 4400 ms | 3.3M |
| Coding | C | Runs well | 24.0 tok/s | 8067 ms | 3.8M |
| Agentic Coding | C | Runs well | 24.0 tok/s | 11733 ms | 3.8M |
| Reasoning | C | Runs well | 24.0 tok/s | 9533 ms | 3.8M |
| RAG | C | Runs well | 24.0 tok/s | 14667 ms | 3.8M |
Quantization options
How Yi Coder 1.5B Chat (1.5B params) fits at each quantization level on NVIDIA L40S 48GB (48.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 0.6 GB | Low | C41 |
Q3_K_S | 3 | 0.7 GB | Low | C41 |
NVFP4 | 4 | 0.8 GB | Medium | C41 |
Q4_K_M | 4 | 0.9 GB | Medium | C41 |
Q5_K_M | 5 | 1.1 GB | High | C41 |
Q6_K | 6 | 1.2 GB | High | C41 |
Q8_0 | 8 | 1.6 GB | Very High | C41 |
F16Best for your GPU | 16 | 3.1 GB | Maximum | C42 |
Get started
Copy-paste commands to run Yi Coder 1.5B Chat on your machine.
Run
lms load hf-maziyarpanahi--yi-coder-1-5b-chat-gguf && lms server startアップグレードオプション
Yi Coder 1.5B Chatを快適に動かすハードウェア
Frequently asked questions
Can NVIDIA L40S 48GB run Yi Coder 1.5B Chat?
Yes, NVIDIA L40S 48GB can run Yi Coder 1.5B Chat with a C grade (Runs well). Expected decode speed: 24.0 tok/s.
How much VRAM does Yi Coder 1.5B Chat need?
Yi Coder 1.5B Chat (1.5B parameters) requires approximately 6.8 GB of memory with Q4_K_M quantization.
What is the best quantization for Yi Coder 1.5B Chat?
The recommended quantization for Yi Coder 1.5B Chat is Q4_K_M, which balances quality and memory efficiency.
What speed will Yi Coder 1.5B Chat run at on NVIDIA L40S 48GB?
On NVIDIA L40S 48GB, Yi Coder 1.5B Chat achieves approximately 24.0 tokens per second decode speed with a time-to-first-token of 8067ms using Q4_K_M quantization.
Can NVIDIA L40S 48GB run Yi Coder 1.5B Chat for coding?
For coding workloads, Yi Coder 1.5B Chat on NVIDIA L40S 48GB receives a C grade with 24.0 tok/s and 3.8M context.
What context window can Yi Coder 1.5B Chat use on NVIDIA L40S 48GB?
On NVIDIA L40S 48GB, Yi Coder 1.5B Chat can safely use up to 3.8M 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-maziyarpanahi--yi-coder-1-5b-chat-gguf-on-l40s-48gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: