RTX 5070 12GBコスパ重視12 GB VRAM (+1)672 GB/s (+188)
B
Raises estimated decode speed by about 48%.77.1 tok/sデコード
Raises estimated decode speed by about 48%.
〜$549 MSRP
Can Qwen3.5 9B run on GTX 1080 Ti 11GB?
YES — Runs Great
B55Good
Estimated from fit model
Qwen3.5 9B needs ~8.8 GB VRAM. GTX 1080 Ti 11GB has 11.0 GB. With Q4_K_M quantization, expect ~52 tok/s.
Runtime: OllamaCapacity: RoomyBandwidth: MediumStack: BasicBottleneck: Balanced
Operating mode
Choose the run profile you care about
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
Q4_K_M (Medium quality) — 8.8 GB, 52.0 tok/s, Runs well
8.8 GB required11.0 GB available
80% VRAM used
Fit status
Runs well
Decode
52.0 tok/s
TTFT
3722 ms
Safe context
49K
Memory
8.8 GB / 11.0 GB
Memory breakdown
Weights5.5 GB
KV Cache1.1 GB
Runtime1.2 GB
Headroom1.1 GB
See how fast it feels
See how fast it feelsQwen3.5 9B on GTX 1080 Ti 11GB
1st promptCold start — includes initialization
>What is local AI inference?
Local AI inference means running an AI language model directly on your own hardware — your laptop, desktop, or server — instead of sending requests to a remote cloud API.
When you run inference locally the model weights are loaded into your GPU or unified memory. Each token you generate requires reading those weights from memory, so memory bandwidth is the main bottleneck for decode speed.
Key benefits of running locally:
- Full privacy: your prompts never leave your machine
- No per-token cost or rate limits
- Works offline once the model is downloaded
- Latency depends only on your hardware
2nd promptWarm — model ready, no init overhead
>How much VRAM do I need?
It depends on the model size and quantization level. A rough rule of thumb:
Model size Q4 (4-bit) Q8 (8-bit) FP16
7B params ~4.3 GB ~7.5 GB ~14 GB
13B params ~7.9 GB ~13.9 GB ~26 GB
70B params ~42.7 GB ~74.9 GB ~140 GB
Most people use 4-bit quantization (Q4_K_M) which gives 90-95% of full quality at a fraction of the memory. A 24 GB GPU can comfortably run most 7B-13B models.
Estimated: 52.0 tok/s decode · 3.7s TTFT (warm) · 130 tok/s prefill
What limits this setup
This setup is broadly balanced for this model.
Older PCIe generation
PCIe 3.0 is workable, but it compounds the penalty when you offload heavily or try to scale across multiple cards.
Best improvement path
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | B | Runs well | 52.0 tok/s | 2030 ms | 49K |
| Coding | B | Runs well | 52.0 tok/s | 3722 ms | 49K |
| Agentic Coding | C | Tight fit | 52.0 tok/s | 5414 ms | 49K |
| Reasoning | B | Runs well | 52.0 tok/s | 4399 ms | 49K |
| RAG | C | Tight fit | 52.0 tok/s | 6767 ms | 49K |
Quantization options
How Qwen3.5 9B (9B params) fits at each quantization level on GTX 1080 Ti 11GB (11.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.5 GB | Low | C51 |
Q3_K_S | 3 | 4.4 GB | Low | C53 |
NVFP4 | 4 | 5.0 GB | Medium | C53 |
Q4_K_M | 4 | 5.5 GB | Medium | C53 |
Q5_K_M | 5 | 6.5 GB | High | C53 |
Q6_KBest for your GPU | 6 | 7.4 GB | High | C52 |
Q8_0 | 8 | 9.6 GB | Very High | F0 |
F16 | 16 | 18.5 GB | Maximum | F0 |
Get started
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 99アップグレードオプション
Qwen3.5 9Bを快適に動かすハードウェア
RTX 5070 12GBコスパ重視RTX 4070 Super 12GBコスパ最良12 GB VRAM (+1)504 GB/s (+20)
B
Raises estimated decode speed by about 36%.70.7 tok/sデコード
Raises estimated decode speed by about 36%.
〜$599 MSRP
RTX 4070 12GBNVIDIAアップグレード12 GB VRAM (+1)504 GB/s (+20)
B
Raises estimated decode speed by about 33%.68.9 tok/sデコード
Raises estimated decode speed by about 33%.
〜$599 MSRP
Frequently asked questions
Can GTX 1080 Ti 11GB run Qwen3.5 9B?
Yes, GTX 1080 Ti 11GB can run Qwen3.5 9B with a B grade (Runs well). Expected decode speed: 52.0 tok/s.
How much VRAM does Qwen3.5 9B need?
Qwen3.5 9B (9B parameters) requires approximately 8.8 GB of memory with Q4_K_M quantization.
What is the best quantization for Qwen3.5 9B?
The recommended quantization for Qwen3.5 9B is Q4_K_M, which balances quality and memory efficiency.
What speed will Qwen3.5 9B run at on GTX 1080 Ti 11GB?
On GTX 1080 Ti 11GB, Qwen3.5 9B achieves approximately 52.0 tokens per second decode speed with a time-to-first-token of 3722ms using Q4_K_M quantization.
Can GTX 1080 Ti 11GB run Qwen3.5 9B for coding?
For coding workloads, Qwen3.5 9B on GTX 1080 Ti 11GB receives a B grade with 52.0 tok/s and 49K context.
What context window can Qwen3.5 9B use on GTX 1080 Ti 11GB?
On GTX 1080 Ti 11GB, Qwen3.5 9B can safely use up to 49K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.
Embed this result▼
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-gtx-1080-ti-11gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: