DeepSeek R1 0528 Qwen3 8B 4bit is an open-source language model by mlx-community. Features: 8b LLM, VRAM: 4.6GB, Context: 128K, License: mit, Quantized, LLM Explorer Score: 0.23.
4-bit 4bit Base model:deepseek-ai/deepsee... Base model:quantized:deepseek-... Conversational Mlx Quantized Qwen3 Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/mlx-community/DeepSeek-R1-0528-Qwen3-8B-4bit
DeepSeek R1 0528 Qwen3 8B 4bit Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
DeepSeek R1 0528 Qwen3 8B 4bit Parameters and Internals
| LLM Name | DeepSeek R1 0528 Qwen3 8B 4bit |
| Repository 🤗 | https://huggingface.co/mlx-community/DeepSeek-R1-0528-Qwen3-8B-4bit |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 4.6 GB |
| Updated | 2026-04-11 |
| Maintainer | mlx-community |
| Model Type | qwen3 |
| Model Files | |
| Quantization Type | 4bit |
| Model Architecture | Qwen3ForCausalLM |
| License | mit |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.51.0 |
| Tokenizer Class | LlamaTokenizerFast |
| Padding Token | <｜end▁of▁sentence｜> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
Best Alternatives to DeepSeek R1 0528 Qwen3 8B 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...0528 Qwen3 8B Unsloth Bnb 4bit | 128K / 7.5 GB | 5866 | 13 |
| ...Seek R1 0528 Qwen3 8B Bnb 4bit | 128K / 6.1 GB | 352 | 10 |
| Qwen3 8B LQA 14e Full | 128K / 16.4 GB | 6 | 0 |
| ...Seek R1 0528 Qwen3 8B 4bit DWQ | 128K / 4.6 GB | 174 | 8 |
| ...0528 Qwen3 8B Unsloth Bnb 4bit | 128K / 16.4 GB | 5 | 0 |
| Annie Lite V0.2.9 Qwen3 8B | 80K / 16.4 GB | 9 | 0 |
| Bonsai 8B Mlx 1bit | 64K / 1.3 GB | 7582 | 114 |
| Bonsai 8B MLX 2.25bit | 64K / 2.3 GB | 443 | 2 |
| Qwen3 8B Unsloth Bnb 4bit | 40K / 7.5 GB | 110145 | 18 |
| Qwen3 8B Bnb 4bit | 40K / 6.1 GB | 40154 | 9 |
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/DeepSeek-R1-0528-Qwen3-8B-4bit .
Rank the DeepSeek R1 0528 Qwen3 8B 4bit Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 52758 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a