MacBook Pro M4 Max 48GBコスパ重視
48 GB Unified (+16)
C
This setup is broadly balanced for this model.76.8 tok/sデコード
〜$2,499 MSRP
Can DeepSeek R1 Distill Llama 8B run on RTX 5090 32GB?
YES — Runs Great
C49Usable
Estimated from fit model
DeepSeek R1 Distill Llama 8B needs ~10.2 GB VRAM. RTX 5090 32GB has 32.0 GB. With Q4_K_M quantization, expect ~112 tok/s.
Runtime: OllamaCapacity: RoomyBandwidth: HighStack: 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) — 10.2 GB, 112.0 tok/s, Runs well
10.2 GB required32.0 GB available
32% VRAM used
Fit status
Runs well
Decode
112.0 tok/s
TTFT
1729 ms
Safe context
388K
Memory
10.2 GB / 32.0 GB
Memory breakdown
Weights4.9 GB
KV Cache0.9 GB
Runtime1.2 GB
Headroom3.2 GB
See how fast it feels
See how fast it feelsDeepSeek R1 Distill Llama 8B on RTX 5090 32GB
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: 112.0 tok/s decode · 1.7s TTFT (warm) · 280 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 | C | Runs well | 112.0 tok/s | 943 ms | 388K |
| Coding | C | Runs well | 112.0 tok/s | 1729 ms | 388K |
| Agentic Coding | C | Runs well | 112.0 tok/s | 2514 ms | 388K |
| Reasoning | C | Runs well | 112.0 tok/s | 2043 ms | 388K |
| RAG | C | Runs well | 112.0 tok/s | 3143 ms | 388K |
Quantization options
How DeepSeek R1 Distill Llama 8B (8B params) fits at each quantization level on RTX 5090 32GB (32.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.1 GB | Low | C43 |
Q3_K_S | 3 | 3.9 GB | Low | C44 |
NVFP4 | 4 | 4.5 GB | Medium | C44 |
Q4_K_M | 4 | 4.9 GB | Medium | C44 |
Q5_K_M | 5 | 5.8 GB | High | C44 |
Q6_K | 6 | 6.6 GB | High | C44 |
Q8_0 | 8 | 8.6 GB | Very High | C45 |
F16Best for your GPU | 16 | 16.4 GB | Maximum | C49 |
Get started
Copy-paste commands to run DeepSeek R1 Distill Llama 8B on your machine.
Run
lms load hf-unsloth--deepseek-r1-distill-llama-8b-gguf && lms server startアップグレードオプション
DeepSeek R1 Distill Llama 8Bを快適に動かすハードウェア
Frequently asked questions
Can RTX 5090 32GB run DeepSeek R1 Distill Llama 8B?
Yes, RTX 5090 32GB can run DeepSeek R1 Distill Llama 8B with a C grade (Runs well). Expected decode speed: 112.0 tok/s.
How much VRAM does DeepSeek R1 Distill Llama 8B need?
DeepSeek R1 Distill Llama 8B (8B parameters) requires approximately 10.2 GB of memory with Q4_K_M quantization.
What is the best quantization for DeepSeek R1 Distill Llama 8B?
The recommended quantization for DeepSeek R1 Distill Llama 8B is Q4_K_M, which balances quality and memory efficiency.
What speed will DeepSeek R1 Distill Llama 8B run at on RTX 5090 32GB?
On RTX 5090 32GB, DeepSeek R1 Distill Llama 8B achieves approximately 112.0 tokens per second decode speed with a time-to-first-token of 1729ms using Q4_K_M quantization.
Can RTX 5090 32GB run DeepSeek R1 Distill Llama 8B for coding?
For coding workloads, DeepSeek R1 Distill Llama 8B on RTX 5090 32GB receives a C grade with 112.0 tok/s and 388K context.
What context window can DeepSeek R1 Distill Llama 8B use on RTX 5090 32GB?
On RTX 5090 32GB, DeepSeek R1 Distill Llama 8B can safely use up to 388K 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--deepseek-r1-distill-llama-8b-gguf-on-rtx-5090-32gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: