Mac Studio M3 Ultra 256GBコスパ重視
256 GB Unified (+128)
B
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.
〜$6,999 MSRP
Can Qwen 2.5 Coder 1.5B run on Gaudi 3 128GB?
YES — Runs Great
B58Good
Estimated from fit model
Qwen 2.5 Coder 1.5B needs ~15.0 GB VRAM. Gaudi 3 128GB has 128.0 GB. With Q4_K_M quantization, expect ~21 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) — 15.0 GB, 21.0 tok/s, Runs well
15.0 GB required128.0 GB available
12% VRAM used
Fit status
Runs well
Decode
21.0 tok/s
TTFT
9219 ms
Safe context
33K
Memory
15.0 GB / 128.0 GB
Memory breakdown
Weights0.9 GB
KV Cache0.4 GB
Runtime0.9 GB
Headroom12.8 GB
See how fast it feels
See how fast it feelsQwen 2.5 Coder 1.5B on Gaudi 3 128GB
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: 21.0 tok/s decode · 9.2s TTFT (warm) · 53 tok/s prefill
What limits this setup
The raw memory story may look fine, but the software ecosystem is still a constraint here.
Runtime ecosystem is narrower than CUDA
Intel GPUs can look attractive on memory per dollar, but local AI tooling, kernels, and model coverage are still broader and easier on CUDA today.
Best improvement path
Prefer CUDA if you want the path of least resistance
If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | B | Runs well | 21.0 tok/s | 5029 ms | 33K |
| Coding | B | Runs well | 21.0 tok/s | 9219 ms | 33K |
| Agentic Coding | B | Runs well | 21.0 tok/s | 13410 ms | 33K |
| Reasoning | B | Runs well | 21.0 tok/s | 10895 ms | 33K |
| RAG | B | Runs well | 21.0 tok/s | 16762 ms | 33K |
Quantization options
How Qwen 2.5 Coder 1.5B (1.5B params) fits at each quantization level on Gaudi 3 128GB (128.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 0.6 GB | Low | B57 |
Q3_K_S | 3 | 0.7 GB | Low | B57 |
NVFP4 | 4 | 0.8 GB | Medium | B57 |
Q4_K_M | 4 | 0.9 GB | Medium | B57 |
Q5_K_M | 5 | 1.1 GB | High | B57 |
Q6_K | 6 | 1.2 GB | High | B57 |
Q8_0 | 8 | 1.6 GB | Very High | B57 |
F16Best for your GPU | 16 | 3.1 GB | Maximum | B57 |
Get started
Copy-paste commands to run Qwen 2.5 Coder 1.5B on your machine.
Run
ollama run qwen2.5-coder:1.5bアップグレードオプション
Qwen 2.5 Coder 1.5Bを快適に動かすハードウェア
Frequently asked questions
Can Gaudi 3 128GB run Qwen 2.5 Coder 1.5B?
Yes, Gaudi 3 128GB can run Qwen 2.5 Coder 1.5B with a B grade (Runs well). Expected decode speed: 21.0 tok/s.
How much VRAM does Qwen 2.5 Coder 1.5B need?
Qwen 2.5 Coder 1.5B (1.5B parameters) requires approximately 15.0 GB of memory with Q4_K_M quantization.
What is the best quantization for Qwen 2.5 Coder 1.5B?
The recommended quantization for Qwen 2.5 Coder 1.5B is Q4_K_M, which balances quality and memory efficiency.
What speed will Qwen 2.5 Coder 1.5B run at on Gaudi 3 128GB?
On Gaudi 3 128GB, Qwen 2.5 Coder 1.5B achieves approximately 21.0 tokens per second decode speed with a time-to-first-token of 9219ms using Q4_K_M quantization.
Can Gaudi 3 128GB run Qwen 2.5 Coder 1.5B for coding?
For coding workloads, Qwen 2.5 Coder 1.5B on Gaudi 3 128GB receives a B grade with 21.0 tok/s and 33K context.
What context window can Qwen 2.5 Coder 1.5B use on Gaudi 3 128GB?
On Gaudi 3 128GB, Qwen 2.5 Coder 1.5B can safely use up to 33K tokens of context. The model's official context limit is 33K, but available memory constrains the safe maximum.
What should I upgrade first if Qwen 2.5 Coder 1.5B feels slow on Gaudi 3 128GB?
Prefer CUDA if you want the path of least resistance. If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.
Would CUDA be a better path than Gaudi 3 128GB for Qwen 2.5 Coder 1.5B?
Often yes, if your goal is the easiest setup and the widest runtime support. Intel can offer attractive memory capacity, but CUDA still tends to win on tooling maturity, guides, kernels, and model coverage for local AI.
Embed this result▼
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/qwen-2.5-coder-1.5b-on-gaudi-3-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: