Mac Studio M3 Ultra 96GBBudget pick
96 GB Unified (+48)819 GB/s (+147)
C
Adds memory headroom for longer context windows and future model growth.112 tok/s decode
Adds memory headroom for longer context windows and future model growth.
~$3,999 MSRP
Can DeepSeek R1 0528 Qwen3 8B run on Quadro RTX 8000 48GB?
YES — Runs Great
C47Usable
○Estimated from fit model
DeepSeek R1 0528 Qwen3 8B needs ~11.8 GB VRAM. Quadro RTX 8000 48GB has 48.0 GB. With Q4_K_M quantization, expect ~95 tok/s.
Runtime: OllamaCapacity: RoomyBandwidth: MediumStack: BasicBottleneck: 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) — 11.8 GB, 95.0 tok/s, Runs well
11.8 GB required48.0 GB available
25% VRAM used
Fit status
Runs well
Decode
95.0 tok/s
TTFT
2038 ms
Safe context
634K
Memory
11.8 GB / 48.0 GB
Memory breakdown
Weights4.9 GB
KV Cache0.9 GB
Runtime1.2 GB
Headroom4.8 GB
See how fast it feels
See how fast it feelsDeepSeek R1 0528 Qwen3 8B on Quadro RTX 8000 48GB
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: 95.0 tok/s decode · 2.0s TTFT (warm) · 238 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 | C | Runs well | 95.0 tok/s | 1111 ms | 634K |
| Coding | C | Runs well | 95.0 tok/s | 2038 ms | 634K |
| Agentic Coding | C | Runs well | 95.0 tok/s | 2964 ms | 634K |
| Reasoning | C | Runs well | 95.0 tok/s | 2408 ms | 634K |
| RAG | C | Runs well | 95.0 tok/s | 3705 ms | 634K |
Quantization options
How DeepSeek R1 0528 Qwen3 8B (8B params) fits at each quantization level on Quadro RTX 8000 48GB (48.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.1 GB | Low | C42 |
Q3_K_S | 3 | 3.9 GB | Low | C42 |
NVFP4 | 4 | 4.5 GB | Medium | C42 |
Q4_K_M | 4 | 4.9 GB | Medium | C42 |
Q5_K_M | 5 | 5.8 GB | High | C42 |
Q6_K | 6 | 6.6 GB | High | C42 |
Q8_0 | 8 | 8.6 GB | Very High | C43 |
F16Best for your GPU | 16 | 16.4 GB | Maximum | C45 |
Get started
Copy-paste commands to run DeepSeek R1 0528 Qwen3 8B on your machine.
Run
lms load hf-unsloth--deepseek-r1-0528-qwen3-8b-gguf && lms server startUpgrade options