Qwen3.5 9B needs ~20.8 GB VRAM. NVIDIA DGX Spark 128GB has 108.8 GB. With Q4_K_M quantization, expect ~30 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 | C | Runs well | 29.8 tok/s | 6489 ms | 1.4M |
| 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 |
Inference speed
Estimated decode speed (tokens/sec) for Qwen3.5 9B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~126 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.
| GPU / Mac | Memory | Quant | Speed (tok/s) | Fits? |
|---|---|---|---|---|
 RTX 5090 32GB | 32 GB | Q4_K_M | 126.0 | Fits |
| RTX 4090 24GB | 24 GB | Q4_K_M | 126.0 | Fits |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 125.9 | Fits |
| RTX 3090 24GB | 24 GB | Q4_K_M | 119.3 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 111.3 | Fits |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 101.4 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 84.5 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 80.1 | Fits |
| RTX 4070 12GB | 12 GB | Q4_K_M | 68.9 | Fits |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 68.3 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 68.3 | Fits |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 43.7 | Fits |
| RTX 3060 12GB | 12 GB | Q4_K_M | 43.3 | Fits |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 40.1 | Fits |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 35.2 | Fits |
| RTX 4060 8GB | 8 GB | Q4_K_M | 23.4 | Offloads |
Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.
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 | 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 |
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
NVIDIA H200 141GBBudget pickRaises estimated decode speed by about 323%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP
NVIDIA H200 PCIe 141GBBest valueRaises estimated decode speed by about 323%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP
NVIDIA B200 180GBNVIDIA upgradeRaises 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 with a C grade (Runs well). Expected decode speed: 29.8 tok/s.
Qwen3.5 9B (9B parameters) requires approximately 20.8 GB of memory with Q4_K_M quantization.
The recommended quantization for Qwen3.5 9B is Q4_K_M, which balances quality and memory efficiency.
On NVIDIA DGX Spark 128GB, Qwen3.5 9B achieves approximately 29.8 tokens per second decode speed with a time-to-first-token of 6489ms using Q4_K_M quantization.
For coding workloads, Qwen3.5 9B on NVIDIA DGX Spark 128GB receives a C grade with 29.8 tok/s and 1.4M context.
On NVIDIA DGX Spark 128GB, Qwen3.5 9B can safely use up to 1.4M tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.
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/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: