Raises estimated decode speed by about 323%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP
Qwen3.5 9B needs ~33.8 GB VRAM. NVIDIA DGX Spark 128GB has 0 MB. With F16 quantization, expect ~12 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
29.8 tok/s
TTFT
6489 ms
Safe context
1.4M
Memory
20.8 GB / 108.8 GB
This setup is broadly balanced for this model.
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.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Runs well | 29.8 tok/s | 3539 ms | 1.4M |
| Coding | F | Too heavy | 5.4 tok/s | 36049 ms | 4K |
| Agentic Coding | C | Runs well | 29.8 tok/s | 9438 ms | 1.4M |
| Reasoning | C | Runs well | 29.8 tok/s | 7669 ms | 1.4M |
| RAG | C | Runs well | 29.8 tok/s | 11798 ms | 1.4M |
How Qwen3.5 9B (9B params) fits at each quantization level on NVIDIA DGX Spark 128GB (92.2 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.5 GB | Low | D40 |
Q3_K_S | 3 | 4.4 GB | Low | D40 |
NVFP4 | 4 |
Copy-paste commands to run Qwen3.5 9B on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "unsloth/Qwen3.5-9B-GGUF" \
--hf-file "Qwen3.5-9B-GGUF-Q4_K_M.gguf" \
-c 4096 -ngl 99Upgrade options
Raises estimated decode speed by about 323%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP
Raises estimated decode speed by about 323%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP
Raises estimated decode speed by about 323%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP
Yes, NVIDIA DGX Spark 128GB can run Qwen3.5 9B at F16 quantization (Runs well). The recommended Q4_K_M requires 7.7 GB which exceeds available memory, but at F16 it needs only 33.8 GB. Expected decode speed: 12.4 tok/s.
Qwen3.5 9B (9B parameters) requires approximately 7.7 GB at Q4_K_M quantization. On NVIDIA DGX Spark 128GB, it fits at F16 using 33.8 GB.
The recommended quantization is Q4_K_M, but on NVIDIA DGX Spark 128GB the best fitting quantization is F16, which uses 33.8 GB.
On NVIDIA DGX Spark 128GB, Qwen3.5 9B achieves approximately 12.4 tokens per second decode speed with a time-to-first-token of 15576ms using F16 quantization.
For coding workloads, Qwen3.5 9B on NVIDIA DGX Spark 128GB receives a F grade with 5.4 tok/s and 4K context.
On NVIDIA DGX Spark 128GB, Qwen3.5 9B can safely use up to 1.2M tokens of context at F16 quantization. The model's official context limit is —, but available memory constrains the safe maximum.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/hf-unsloth--qwen3-5-9b-gguf-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:
5.0 GB |
| Medium |
| D40 |
Q4_K_M | 4 | 5.5 GB | Medium | D40 |
Q5_K_M | 5 | 6.5 GB | High | D40 |
Q6_K | 6 | 7.4 GB | High | D40 |
Q8_0 | 8 | 9.6 GB | Very High | D40 |
F16Best for your GPU | 16 | 18.5 GB | Maximum | C41 |
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.