12 GB VRAM (+4)360 GB/s (+104)
C
Raises estimated decode speed by about 94%.36.4 tok/s decode
Raises estimated decode speed by about 94%.
Adds memory headroom for longer context windows and future model growth.
~$329 MSRP
Can Qwen3.5 9B run on GTX 1070 8GB?
YES — With Offload
C49Usable
○Estimated from fit model
Qwen3.5 9B needs ~8.2 GB VRAM. GTX 1070 8GB has 8.0 GB. With Q4_K_M quantization, expect ~19 tok/s.
Runtime: llama.cppCapacity: OffloadBandwidth: LowStack: StandardBottleneck: Balanced
Share:
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) — 8.2 GB, 18.8 tok/s, Runs with offload (needs ~0.2 GB host RAM)
8.2 GB required8.0 GB available
102% VRAM needed
0.2 GB over capacity — needs offload or smaller quantization
Fit status
Runs with offload (needs ~0.2 GB host RAM)
Decode
18.8 tok/s
TTFT
10307 ms
Safe context
12K
Memory
8.2 GB / 8.0 GB
Memory breakdown
Weights5.5 GB
KV Cache1.1 GB
Runtime0.9 GB
Headroom0.8 GB
See how fast it feels
See how fast it feelsQwen3.5 9B on GTX 1070 8GB
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: 18.8 tok/s decode · 10.3s TTFT (warm) · 47 tok/s prefill
What limits this setup
This setup is broadly balanced for this model.
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.
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
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Runs with offload | 27.5 tok/s | 3838 ms | 12K |
| Coding | C | Runs with offload (needs ~0.2 GB host RAM) | 18.8 tok/s | 10307 ms | 12K |
| Agentic Coding | D | Very compromised (needs ~0.8 GB host RAM) | 14.4 tok/s | 19529 ms | 12K |
| Reasoning | C | Runs with offload (needs ~0.2 GB host RAM) | 18.8 tok/s | 12181 ms | 12K |
| RAG | D | Very compromised (needs ~0.8 GB host RAM) | 14.4 tok/s | 24411 ms | 12K |
Quantization options
How Qwen3.5 9B (9B params) fits at each quantization level on GTX 1070 8GB (8.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.5 GB | Low | C54 |
Q3_K_S | 3 | 4.4 GB | Low | C53 |
NVFP4Best for your GPU | 4 | 5.0 GB | Medium | C53 |
Q4_K_M | 4 | 5.5 GB | Medium | F0 |
Q5_K_M | 5 | 6.5 GB | High | F0 |
Q6_K | 6 | 7.4 GB | High | F0 |
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 99Upgrade options
Hardware that runs Qwen3.5 9B well
16 GB VRAM (+8)448 GB/s (+192)
C
Raises estimated decode speed by about 169%.50.6 tok/s decode
Raises estimated decode speed by about 169%.
Adds memory headroom for longer context windows and future model growth.
~$449 MSRP
16 GB VRAM (+8)288 GB/s (+32)
C
Raises estimated decode speed by about 87%.35.2 tok/s decode
Raises estimated decode speed by about 87%.
Adds memory headroom for longer context windows and future model growth.
~$499 MSRP