Qwen 3 235B A22B needs ~148.2 GB VRAM. Gaudi 3 128GB has 128.0 GB. With NVFP4 quantization, expect ~34 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
31.9 GB over capacity — needs offload or smaller quantization
Fit status
Too heavy
Decode
25.6 tok/s
TTFT
7564 ms
Safe context
4K
Memory
159.9 GB / 128.0 GB
Offload
20%
It fits through host-memory offload, and offload is the main reason performance drops.
CPU or host-memory offload is active
About 10% of the working set spills out of accelerator memory, which usually hurts latency and sustained decode throughput.
Very little memory headroom
You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.
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.
Remove offload with more accelerator memory
Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.
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.
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | F | Too heavy | 26.1 tok/s | 4051 ms | 4K |
| Coding | F | Too heavy | 25.6 tok/s | 7564 ms | 4K |
| Agentic Coding | F | Too heavy | 24.7 tok/s | 11408 ms | 4K |
| Reasoning | F | Too heavy | 25.6 tok/s | 8939 ms | 4K |
| RAG | F | Too heavy | 24.7 tok/s | 14260 ms | 4K |
How Qwen 3 235B A22B (235B params) fits at each quantization level on Gaudi 3 128GB (128.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_KBest for your GPU | 2 | 91.7 GB | Low | S86 |
Q3_K_S | 3 | 115.2 GB | Low | F0 |
NVFP4 | 4 | 131.6 GB | Medium | F0 |
Q4_K_M | 4 | 143.4 GB | Medium | F0 |
Q5_K_M | 5 | 169.2 GB | High | F0 |
Q6_K | 6 | 192.7 GB | High | F0 |
Q8_0 | 8 | 251.5 GB | Very High | F0 |
F16 | 16 | 481.7 GB | Maximum | F0 |
Copy-paste commands to run Qwen 3 235B A22B on your machine.
Run
lms load Qwen3-235B-A22B-Instruct-2507 && lms server startOpciones de mejora
Hace que el modelo quepa en el acelerador en lugar de seguir fuera de alcance.
Elimina el offload a memoria del sistema, que suele ser la mayor mejora individual en latencia y throughput.
~$6,999 MSRP
Hace que el modelo quepa en el acelerador en lugar de seguir fuera de alcance.
Elimina el offload a memoria del sistema, que suele ser la mayor mejora individual en latencia y throughput.
~$8,000 MSRP
Yes, Gaudi 3 128GB can run Qwen 3 235B A22B at NVFP4 quantization (Very compromised (needs ~17.9 GB host RAM)). The recommended Q4_K_M requires 159.9 GB which exceeds available memory, but at NVFP4 it needs only 148.2 GB. Expected decode speed: 34.2 tok/s.
Qwen 3 235B A22B (235B parameters) requires approximately 159.9 GB at Q4_K_M quantization. On Gaudi 3 128GB, it fits at NVFP4 using 148.2 GB.
The recommended quantization is Q4_K_M, but on Gaudi 3 128GB the best fitting quantization is NVFP4, which uses 148.2 GB.
On Gaudi 3 128GB, Qwen 3 235B A22B achieves approximately 34.2 tokens per second decode speed with a time-to-first-token of 5660ms using NVFP4 quantization.
For coding workloads, Qwen 3 235B A22B on Gaudi 3 128GB receives a F grade with 25.6 tok/s and 4K context.
On Gaudi 3 128GB, Qwen 3 235B A22B can safely use up to 4K tokens of context at NVFP4 quantization. The model's official context limit is 131K, but available memory constrains the safe maximum.
Remove offload with more accelerator memory. Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.
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.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/qwen-3-235b-a22b-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: