Yi 1.5 34B needs ~38.1 GB VRAM. Gaudi 3 128GB has 128.0 GB. With Q4_K_M quantization, expect ~136 tok/s.
Operating mode
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
Fit status
Runs well
Decode
135.6 tok/s
TTFT
1428 ms
Safe context
4K
Memory
38.1 GB / 128.0 GB
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.
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.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | B | Runs well | 135.6 tok/s | 779 ms | 4K |
| Coding | B | Runs well | 135.6 tok/s | 1428 ms | 4K |
| Agentic Coding | B | Runs well | 135.6 tok/s | 2077 ms | 4K |
| Reasoning | B | Runs well | 135.6 tok/s | 1688 ms | 4K |
| RAG | B | Runs well | 135.6 tok/s | 2596 ms | 4K |
How Yi 1.5 34B (34B params) fits at each quantization level on Gaudi 3 128GB (128.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 13.3 GB | Low | C51 |
Q3_K_S | 3 | 16.7 GB | Low | C51 |
NVFP4 | 4 |
Copy-paste commands to run Yi 1.5 34B on your machine.
Run
lms load Yi-1.5-34B-Chat && lms server startYes, Gaudi 3 128GB can run Yi 1.5 34B with a B grade (Runs well). Expected decode speed: 135.6 tok/s.
Yi 1.5 34B (34B parameters) requires approximately 38.1 GB of memory with Q4_K_M quantization.
The recommended quantization for Yi 1.5 34B is Q4_K_M, which balances quality and memory efficiency.
On Gaudi 3 128GB, Yi 1.5 34B achieves approximately 135.6 tokens per second decode speed with a time-to-first-token of 1428ms using Q4_K_M quantization.
For coding workloads, Yi 1.5 34B on Gaudi 3 128GB receives a B grade with 135.6 tok/s and 4K context.
On Gaudi 3 128GB, Yi 1.5 34B can safely use up to 4K tokens of context. The model's official context limit is 4K, but available memory constrains the safe maximum.
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.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/yi-1.5-34b-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:
| Medium |
| C52 |
Q4_K_M | 4 | 20.7 GB | Medium | C52 |
Q5_K_M | 5 | 24.5 GB | High | C52 |
Q6_K | 6 | 27.9 GB | High | C53 |
Q8_0 | 8 | 36.4 GB | Very High | C54 |
F16Best for your GPU | 16 | 69.7 GB | Maximum | B60 |
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.