MaziyarPanahi
DeepSeek R1 0528 Qwen3 8B (8B parameters) requires approximately 7.6 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 9 GB of VRAM.
Quick specs
Related models
Inference speed
Estimated decode speed (tokens/sec) for DeepSeek R1 0528 Qwen3 8B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~112 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.
| GPU / Mac | Memory | Quant | Speed (tok/s) | Fits? |
|---|---|---|---|---|
 RTX 5090 32GB | 32 GB | Q4_K_M | 112.0 | Fits |
| RTX 4090 24GB | 24 GB | Q4_K_M | 112.0 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 112.0 |
Quick picks
Best hardware
Run this model
Quantization
How much VRAM DeepSeek R1 0528 Qwen3 8B (8B) needs at each GGUF quant, and whether it fits a 24 GB card (RTX 4090 / 3090). The recommended Q4_K_M uses ~4.9 GB — about 43% less VRAM than Q8_0, at a small quality cost.
| Quant | Bits | VRAM (weights) | Quality | Fits 24 GB? |
|---|---|---|---|---|
| Q2_K | 2 | 3.1 GB | Low | Fits |
| Q3_K_S | 3 | 3.9 GB | Low | Fits |
| NVFP4 | 4 | 4.5 GB | Medium | Fits |
| Q4_K_Mrecommended | 4 | 4.9 GB | Medium | Fits |
Hardware compatibility
Computing compatibility...
Memory breakdown
Frequently asked questions
DeepSeek R1 0528 Qwen3 8B (8B parameters) requires approximately 7.6 GB of VRAM with Q4_K_M quantization. Lower quantizations like Q4_K_M use less memory but may reduce quality.
Yes, Intel Arc A580 8GB can run DeepSeek R1 0528 Qwen3 8B with a compatibility score of 52/100. It provides 8 GB of memory and achieves approximately 51.4 tokens per second.
The recommended quantization for DeepSeek R1 0528 Qwen3 8B is Q4_K_M, which offers the best balance between model quality and memory efficiency. Higher quantizations preserve more quality but require more VRAM.
The top recommended hardware for DeepSeek R1 0528 Qwen3 8B: RTX 3080 10GB (score: 57/100), RTX 2080 Ti 11GB (score: 57/100), RTX 3080 Ti 12GB (score: 57/100). These provide the best combination of memory, bandwidth, and compute for running this model locally.
Yes, DeepSeek R1 0528 Qwen3 8B is well-suited for chat as well as reasoning. It was designed with these use cases in mind.
See also
| Fits |
| RTX 3090 24GB | 24 GB | Q4_K_M | 112.0 | Fits |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 112.0 | Fits |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 112.0 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 95.1 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 90.2 | Fits |
| RTX 4070 12GB | 12 GB | Q4_K_M | 77.5 | Fits |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 76.8 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 76.8 | Fits |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 49.2 | Fits |
| RTX 3060 12GB | 12 GB | Q4_K_M | 48.7 | Fits |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 45.1 | Fits |
| RTX 4060 8GB | 8 GB | Q4_K_M | 40.7 | Offloads |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 39.6 | Fits |
Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.
| Q5_K_M |
| 5 |
| 5.8 GB |
| High |
| Fits |
| Q6_K | 6 | 6.6 GB | High | Fits |
| Q8_0 | 8 | 8.6 GB | Very High | Fits |
| F16 | 16 | 16.4 GB | Maximum | Tight |
VRAM shown is quantized weights only; add ~1–3 GB runtime overhead plus KV cache for your context length. Lower quants trade quality for memory — Q4_K_M is the usual sweet spot; Q2/Q3 only when you must fit a bigger model.
