DeepSeek R1 0528 Qwen3 8B — Hardware Requirements & GPU Compatibility
ChatReasoningFunctions
With about 8 billion parameters, DeepSeek R1 0528 Qwen3 8B is a dated May 2025 release in DeepSeek's R1 line, built on a Qwen3-based architecture rather than DeepSeek's own base model. It supports explicit step-by-step reasoning, generating intermediate reasoning traces before producing a final answer, which sets it apart from standard instruction-tuned chat models that answer directly. Its modest size means it runs comfortably on modest consumer GPUs, making it accessible for local experimentation with reasoning-style outputs without specialized hardware. It offers a 128K token context window, ample for most reasoning and coding tasks, and is released under the MIT license, allowing broad local and commercial use.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 16K)Best on 24 GB (Q4_K_M · ~119 tok/s · 64K)Macs from 16 GB (Q4_K_M · ~25 tok/s)
MIT
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run DeepSeek R1 0528 Qwen3 8B
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
ollama run deepseek-r1:8bQ4_K_M fits fully on the RTX 4090 · 16.4 GB free · 16K context
Download: DeepSeek-R1-0528-Qwen3-8B-Q4_K_M.gguf5.03 GBunsloth
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (4 GB headroom) · Q4_K_M
- Generation speed
- ~42 tok/s
- generation speed
- Cost per 1M output tokens
- $0.54
- per 1M output tokens
How Much VRAM Does DeepSeek R1 0528 Qwen3 8B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 4.1 GB | 8.6 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 128K context · ~161 tok/s | |
| 4.2 GB | 8.7 GB | 3-bit small — 3-bit small quantization | Fits: 128K context · ~156 tok/s | |
| 4.6 GB | 9.1 GB | 3-bit medium — 3-bit medium quantization | Fits: 128K context · ~143 tok/s | |
| 4.7 GB | 9.2 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 128K context · ~139 tok/s | |
| 5.5 GB | 10.1 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 64K context · ~119 tok/s | |
| 6.4 GB | 11 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 64K context · ~102 tok/s | |
| 7.4 GB | 11.9 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 64K context · ~89 tok/s | |
| 8.8 GB | 13.3 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 64K context · ~75 tok/s |
Selected Q4_K_M
4-bit medium quantization7.6GBat 16K context
- Weights
- 4.9 GB
- KV cache
- 2.4 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 16.4 GB free · ~119 tok/s
≥50 tok/s needs ≥424 GB/s · RTX 5090 ~211, RTX 3090 Ti ~119
Which Hardware Can Run DeepSeek R1 0528 Qwen3 8B?
Q4_K_M · 5.5 GBDeepSeek R1 0528 Qwen3 8B (Q4_K_M) requires 5.5 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 8+ GB is recommended. Using the full 131K context window can add up to 19.0 GB, bringing total usage to 24.5 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3070 Ti. 151 devices with unified memory can run DeepSeek R1 0528 Qwen3 8B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), NVIDIA Jetson Orin Nano 8GB (Super).
≤ 11 GB
≤ 11 GB tier →fits · 0.4 GB free · up to 16K ctx
16 GPUs · 1 device family
RTX 3080~90Simulate output on RTX 3080RTX 2080 Ti~73Simulate output on RTX 2080 TiRTX 3070 Ti~72Simulate output on RTX 3070 TiOrin Nano~12Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)20 GB
fits · 12.4 GB free · up to 64K ctx
1 GPU
RX 7900 XT~87Simulate output on RX 7900 XT32–40 GB
fits · 24.4 GB free · up to 128K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~211Simulate output on RTX 5090M5 Max36 GB~58Simulate output on Mac Studio M5 Max (36 GB)M532 GB~20Simulate output on MacBook Air 13" M5 (32 GB)Orin~24Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~16Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
How good is DeepSeek R1 0528 Qwen3 8B?
llmrun Score blends public benchmark boards into one number; 100 = the average open model.
Not enough data yet for an llmrun Score.
A Score needs results on enough independent boards. How the Composite Score is built
Benchmarks
Here are all 2 boards that have results for this model, sorted by their weight in the llmrun Score; badges show who ran the test.
- GPQA Diamond
Epoch AI · May 2025Independent
Independent9.3%
#98/98 open
- AIME 2024/2025
Epoch AI · May 2025Independent
Independent43.9%
#47/86 open
Alternatives to DeepSeek R1 0528 Qwen3 8B
DeepSeek R1 family · 13 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Granite Switch 4.1 8BIBM | — | 20.7 GB | ~36 | same size |
| ALoDLM 8BAmazon | — | 7.6 GB | ~119 | same size |
| Llm Jp 4.1 8B Thinkingllm-jp | — | 7.6 GB | ~115 | same size |
| Ling 3.0 TinyInclusion AI | — | 5.5 GB | ~364 | same size |
| LFM2.5 8B A1BLiquid AI | — | 5.6 GB | ~335 | same size |
| BitCPM CANN 8BOpenBMB | — | 5.6 GB | ~127 | same size |
Specifications
- Publisher
- DeepSeek
- Family
- DeepSeek R1
- Parameters
- 8.2B
- Architecture
- Qwen3ForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 151,936
- Release Date
- 2025-05-29
- License
- MIT
Frequently Asked Questions
How much VRAM does DeepSeek R1 0528 Qwen3 8B need?
DeepSeek R1 0528 Qwen3 8B requires 5.5 GB of VRAM at Q4_K_M, or 17.0 GB at BF16. Full 131K context adds up to 19.0 GB (24.5 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 8.2B × 4.8 bits ÷ 8 = 4.9 GB
KV Cache + Overhead ≈ 0.6 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 19.6 GB (at full 131K context)
VRAM usage by quantization
What's the best quantization for DeepSeek R1 0528 Qwen3 8B?
For DeepSeek R1 0528 Qwen3 8B, Q4_K_M (5.5 GB) offers the best balance of quality and VRAM usage. Q4_K_L (5.6 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 2.9 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run DeepSeek R1 0528 Qwen3 8B on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run DeepSeek R1 0528 Qwen3 8B. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 5.5 GB of usable unified memory (RAM minus macOS overhead).
Can I run DeepSeek R1 0528 Qwen3 8B locally?
Yes — DeepSeek R1 0528 Qwen3 8B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is DeepSeek R1 0528 Qwen3 8B?
At Q4_K_M, DeepSeek R1 0528 Qwen3 8B can reach ~870 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~119 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 5.52 × 0.65 = ~942 tok/s
Estimated speed at Q4_K_M (5.5 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of DeepSeek R1 0528 Qwen3 8B?
At Q4_K_M, the download is about 4.91 GB. The full-precision BF16 version is 16.38 GB. The smallest option (IQ2_XXS) is 2.25 GB.
Which GPUs can run DeepSeek R1 0528 Qwen3 8B?
52 consumer GPUs can run DeepSeek R1 0528 Qwen3 8B at Q4_K_M. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 7600. 40 GPUs have plenty of headroom for comfortable inference.
Which devices can run DeepSeek R1 0528 Qwen3 8B?
151 devices with unified memory can run DeepSeek R1 0528 Qwen3 8B at Q4_K_M (5.5 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.