Will It Run AI

Can Qwen 3.5 9B run on RTX 2070 Super 8GB?

BARELY — Tight on Memory

A82Great
Estimated from fit model

Qwen 3.5 9B needs ~9.4 GB VRAM. RTX 2070 Super 8GB has 8.0 GB. With Q4_K_M quantization, expect ~28 tok/s.

Runtime: llama.cppCapacity: OffloadBandwidth: LowStack: StandardBottleneck: Host offload
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.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 9.4 GB, 27.5 tok/s, Very compromised (needs ~0.8 GB host RAM)
9.4 GB required8.0 GB available
118% VRAM needed

1.4 GB over capacity — needs offload or smaller quantization

Fit status

Very compromised (needs ~0.8 GB host RAM)

Decode

27.5 tok/s

TTFT

7047 ms

Safe context

6K

Memory

9.4 GB / 8.0 GB

Offload

10%

Memory breakdown

Weights5.5 GB
KV Cache2.2 GB
Runtime0.9 GB
Headroom0.8 GB

See how fast it feels

See how fast it feelsQwen 3.5 9B on RTX 2070 Super 8GB
1st promptCold start — includes initialization
>Write a Python function to sort a list
Here's a Python function that sorts a list using quicksort: def quicksort(arr): if len(arr) <= 1: return arr pivot = arr[len(arr) // 2] left = [x for x in arr if x < pivot] middle = [x for x in arr if x == pivot] right = [x for x in arr if x > pivot] return quicksort(left) + middle + quicksort(right) # Example usage numbers = [3, 6, 8, 10, 1, 2, 1] print(quicksort(numbers)) # [1, 1, 2, 3, 6, 8, 10] The algorithm picks a pivot, partitions the list into smaller, equal, and larger elements, then recursively sorts each partition and concatenates the results.
2nd promptWarm — model ready, no init overhead
>Now add type hints and a docstring
def quicksort(arr: list[int]) -> list[int]: """Sort a list using the quicksort algorithm. Args: arr: List of integers to sort. Returns: A new sorted list. """ if len(arr) <= 1: return arr pivot = arr[len(arr) // 2] left = [x for x in arr if x < pivot] middle = [x for x in arr if x == pivot] right = [x for x in arr if x > pivot] return quicksort(left) + middle + quicksort(right) Added type hints for the input and return type, plus a Google-style docstring.
Estimated: 27.5 tok/s decode · 7.0s TTFT (warm) · 69 tok/s prefill

What limits this setup

It fits through host-memory offload, and offload is the main reason performance drops.

CPU or host-memory offload is active

About 10% of the working set spills out of accelerator memory, which usually hurts latency and sustained decode throughput.

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

Remove offload with more accelerator memory

Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.

Buy headroom, not only minimum fit

A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

Increase host RAM if you keep offloading

This setup may need roughly 0.8 GB of extra host RAM just for the offloaded portion, before OS and other tools.

Performance by workload

WorkloadGradeFitDecodeTTFTContext
ChatSRuns with offload (needs ~0.2 GB host RAM)36.1 tok/s2924 ms6K
CodingAVery compromised (needs ~0.8 GB host RAM)27.5 tok/s7047 ms6K
Agentic CodingFToo heavy17.3 tok/s16267 ms6K
ReasoningAVery compromised (needs ~0.8 GB host RAM)27.5 tok/s8328 ms6K
RAGFToo heavy17.3 tok/s20334 ms6K

Quantization options

How Qwen 3.5 9B (9B params) fits at each quantization level on RTX 2070 Super 8GB (8.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
3.5 GB
LowS95
Q3_K_S
3
4.4 GB
LowS95
NVFP4Best for your GPU
4
5.0 GB
MediumS94
Q4_K_M
4
5.5 GB
MediumF0
Q5_K_M
5
6.5 GB
HighF0
Q6_K
6
7.4 GB
HighF0
Q8_0
8
9.6 GB
Very HighF0
F16
16
18.5 GB
MaximumF0

Get started

Copy-paste commands to run Qwen 3.5 9B on your machine.

Run

ollama run qwen3.5:9b

Frequently asked questions

Can RTX 2070 Super 8GB run Qwen 3.5 9B?

Yes, RTX 2070 Super 8GB can run Qwen 3.5 9B with a A grade (Very compromised (needs ~0.8 GB host RAM)). Expected decode speed: 27.5 tok/s.

How much VRAM does Qwen 3.5 9B need?

Qwen 3.5 9B (9B parameters) requires approximately 9.4 GB of memory with Q4_K_M quantization.

What is the best quantization for Qwen 3.5 9B?

The recommended quantization for Qwen 3.5 9B is Q4_K_M, which balances quality and memory efficiency.

What speed will Qwen 3.5 9B run at on RTX 2070 Super 8GB?

On RTX 2070 Super 8GB, Qwen 3.5 9B achieves approximately 27.5 tokens per second decode speed with a time-to-first-token of 7047ms using Q4_K_M quantization.

Can RTX 2070 Super 8GB run Qwen 3.5 9B for coding?

For coding workloads, Qwen 3.5 9B on RTX 2070 Super 8GB receives a A grade with 27.5 tok/s and 6K context.

What context window can Qwen 3.5 9B use on RTX 2070 Super 8GB?

On RTX 2070 Super 8GB, Qwen 3.5 9B can safely use up to 6K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.

What should I upgrade first if Qwen 3.5 9B feels slow on RTX 2070 Super 8GB?

Remove offload with more accelerator memory. Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.

See all results for RTX 2070 Super 8GBSee all hardware for Qwen 3.5 9B
Embed this result▼

Paste this snippet into any page to show a live fit card.

<iframe src="https://willitrunai.com/embed/qwen-3.5-9b-on-rtx-2070-super-8gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: