Can DeepSeek R1 0528 Qwen3 8B run on RTX 4070 Super 12GB?

YES — Runs Great

B56Good

Estimated from fit model

DeepSeek R1 0528 Qwen3 8B needs ~8.2 GB VRAM. RTX 4070 Super 12GB has 12.0 GB. With Q4_K_M quantization, expect ~80 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.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 8.2 GB, 79.5 tok/s, Runs well

8.2 GB required12.0 GB available

68% VRAM used

Fit status

Runs well

Decode

79.5 tok/s

TTFT

2434 ms

Safe context

81K

Memory

8.2 GB / 12.0 GB

Memory breakdown

Weights4.9 GB

KV Cache0.9 GB

Runtime1.2 GB

Headroom1.2 GB

See how fast it feels

See how fast it feelsDeepSeek R1 0528 Qwen3 8B on RTX 4070 Super 12GB
1st promptCold start — includes initialization
>Solve: If a train travels at 60 mph for 2.5 hours, how far does it go?
Let me work through this step by step.

Given information:
  - Speed = 60 mph (miles per hour)
  - Time  = 2.5 hours

Formula: Distance = Speed x Time

Calculation:
  Distance = 60 mph x 2.5 h
           = 150 miles

The train travels 150 miles.

Double-check: at 60 mph the train covers 60 miles each hour. In half an hour it covers 30 miles. So in 2.5 hours: 60 + 60 + 30 = 150 miles. Confirmed.
2nd promptWarm — model ready, no init overhead
>What if the train stops for 20 minutes halfway?
The stop doesn't change the total distance covered while moving, but it affects total trip time.

Breakdown:
  - First half: 1.25 hours at 60 mph = 75 miles
  - Stop: 20 minutes (no distance)
  - Second half: 1.25 hours at 60 mph = 75 miles

Total distance: 150 miles (same)
Total time: 2.5 h + 0.33 h = 2.83 hours
Average speed: 150 / 2.83 = 53 mph

The distance stays the same but average speed drops to 53 mph because of the stop.
Estimated: 79.5 tok/s decode · 2.4s TTFT (warm) · 199 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

No major red flags

This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.

Best improvement path

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	B	Runs well	79.5 tok/s	1328 ms	81K
Coding	B	Runs well	79.5 tok/s	2434 ms	81K
Agentic Coding	B	Runs well	79.5 tok/s	3541 ms	81K
Reasoning	B	Runs well	79.5 tok/s	2877 ms	81K
RAG	B	Runs well	79.5 tok/s	4426 ms	81K

Quantization options

How DeepSeek R1 0528 Qwen3 8B (8B params) fits at each quantization level on RTX 4070 Super 12GB (12.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	3.1 GB	Low	C50
Q3_K_S	3	3.9 GB	Low	C51
NVFP4	4	4.5 GB	Medium	C51
Q4_K_M	4	4.9 GB	Medium	C52
Q5_K_M	5	5.8 GB	High	C53
Q6_K	6	6.6 GB	High	C52
Q8_0Best for your GPU	8	8.6 GB	Very High	C52
F16	16	16.4 GB	Maximum	F0

Get started

Copy-paste commands to run DeepSeek R1 0528 Qwen3 8B on your machine.

Run

lms load hf-lmstudio-community--deepseek-r1-0528-qwen3-8b-gguf && lms server start

Frequently asked questions

Can RTX 4070 Super 12GB run DeepSeek R1 0528 Qwen3 8B?

Yes, RTX 4070 Super 12GB can run DeepSeek R1 0528 Qwen3 8B with a B grade (Runs well). Expected decode speed: 79.5 tok/s.

How much VRAM does DeepSeek R1 0528 Qwen3 8B need?

DeepSeek R1 0528 Qwen3 8B (8B parameters) requires approximately 8.2 GB of memory with Q4_K_M quantization.

What is the best quantization for DeepSeek R1 0528 Qwen3 8B?

The recommended quantization for DeepSeek R1 0528 Qwen3 8B is Q4_K_M, which balances quality and memory efficiency.

What speed will DeepSeek R1 0528 Qwen3 8B run at on RTX 4070 Super 12GB?

On RTX 4070 Super 12GB, DeepSeek R1 0528 Qwen3 8B achieves approximately 79.5 tokens per second decode speed with a time-to-first-token of 2434ms using Q4_K_M quantization.

Can RTX 4070 Super 12GB run DeepSeek R1 0528 Qwen3 8B for coding?

For coding workloads, DeepSeek R1 0528 Qwen3 8B on RTX 4070 Super 12GB receives a B grade with 79.5 tok/s and 81K context.

What context window can DeepSeek R1 0528 Qwen3 8B use on RTX 4070 Super 12GB?

On RTX 4070 Super 12GB, DeepSeek R1 0528 Qwen3 8B can safely use up to 81K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

See all results for RTX 4070 Super 12GB See all hardware for DeepSeek R1 0528 Qwen3 8B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/hf-lmstudio-community--deepseek-r1-0528-qwen3-8b-gguf-on-rtx-4070-super-12gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: