Qwen 3 235B A22B needs ~108.5 GB VRAM. NVIDIA DGX Spark 128GB has 108.8 GB. With Q2_K quantization, expect ~4 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
51.4 GB over capacity — needs offload or smaller quantization
Fit status
Too heavy
Decode
2.0 tok/s
TTFT
96800 ms
Safe context
4K
Memory
160.2 GB / 108.8 GB
Offload
30%
The model fits in shared memory, but shared-memory bandwidth is now the real limiter.
Fit does not mean dedicated-VRAM speed
Unified or shared memory can make a model technically fit, but sustained tokens per second may still trail a discrete high-bandwidth GPU with less total memory.
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.
Shared-memory contention still exists
The OS, browser, and inference runtime all compete for the same physical memory pool, so real-world headroom is less forgiving than raw capacity suggests.
Prioritize bandwidth, not only capacity
If this workload feels slow, the next useful step is often a GPU tier with materially faster memory bandwidth rather than only a small bump in capacity.
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 | 2.0 tok/s | 52800 ms | 4K |
| Coding | F | Too heavy | 2.0 tok/s | 96800 ms | 4K |
| Agentic Coding | F | Too heavy | 2.0 tok/s | 140800 ms | 4K |
| Reasoning | F | Too heavy | 2.0 tok/s | 114400 ms | 4K |
| RAG | F | Too heavy | 2.0 tok/s | 176000 ms | 4K |
How Qwen 3 235B A22B (235B params) fits at each quantization level on NVIDIA DGX Spark 128GB (92.2 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 91.7 GB | Low | F0 |
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
NVIDIA B200 180GBOpción económicaHace 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.
~$30,000 MSRP
NVIDIA H200 141GBMejor relación calidad-precioHace que el modelo quepa en el acelerador en lugar de seguir fuera de alcance.
Sube la velocidad estimada de decodificación alrededor de un 2705%.
~$30,000 MSRP
NVIDIA H200 PCIe 141GBMejora NVIDIAHace que el modelo quepa en el acelerador en lugar de seguir fuera de alcance.
Sube la velocidad estimada de decodificación alrededor de un 2285%.
~$30,000 MSRP
Yes, NVIDIA DGX Spark 128GB can run Qwen 3 235B A22B at Q2_K quantization (Runs with offload). The recommended Q4_K_M requires 160.2 GB which exceeds available memory, but at Q2_K it needs only 108.5 GB. Expected decode speed: 4.4 tok/s.
Qwen 3 235B A22B (235B parameters) requires approximately 160.2 GB at Q4_K_M quantization. On NVIDIA DGX Spark 128GB, it fits at Q2_K using 108.5 GB.
The recommended quantization is Q4_K_M, but on NVIDIA DGX Spark 128GB the best fitting quantization is Q2_K, which uses 108.5 GB.
On NVIDIA DGX Spark 128GB, Qwen 3 235B A22B achieves approximately 4.4 tokens per second decode speed with a time-to-first-token of 43681ms using Q2_K quantization.
For coding workloads, Qwen 3 235B A22B on NVIDIA DGX Spark 128GB receives a F grade with 2.0 tok/s and 4K context.
On NVIDIA DGX Spark 128GB, Qwen 3 235B A22B can safely use up to 18K tokens of context at Q2_K quantization. The model's official context limit is 131K, but available memory constrains the safe maximum.
Prioritize bandwidth, not only capacity. If this workload feels slow, the next useful step is often a GPU tier with materially faster memory bandwidth rather than only a small bump in capacity.
Not always. NVIDIA DGX Spark 128GB can often fit larger models thanks to unified memory, but a discrete GPU with dedicated high-bandwidth VRAM may still decode faster once the model fits. For this combination, the important distinction is capacity versus sustained throughput.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/qwen-3-235b-a22b-on-dgx-spark-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: