Deepseek Coder 33B Base — Hardware Requirements & GPU Compatibility
ChatCode
DeepSeek-Coder-33B-Base is DeepSeek's 33.3-billion-parameter base (pretrained, not instruction-tuned) code model, trained from scratch on 2 trillion tokens (87% code, 13% natural language in English and Chinese) using grouped-query attention, project-level code context, and a fill-in-the-blank training objective for project-level completion and infilling. It is intended as a foundation for further fine-tuning or direct code completion and infilling use, not conversational use; the instruction-tuned DeepSeek-Coder-33B-Instruct is built on top of it. At release, the Deepseek Coder family achieved state-of-the-art open-model results on HumanEval, MultiPL-E, MBPP, DS-1000, and APPS. At 33.3 billion parameters, it needs a high-end consumer GPU or a multi-GPU setup once quantized. Context length is 16,384 tokens. Model weights are released under DeepSeek's custom model license, which permits commercial use. It was published in October 2023, alongside 1.3B, 5.7B, and 6.7B siblings and the corresponding instruct checkpoint.
1.9K downloads
78 likesSpecifications
- Publisher
- DeepSeek
- Family
- DeepSeek Coder
- Parameters
- 33.3B
- Architecture
- LlamaForCausalLM
- Context Length
- 16,384 tokens
- Vocabulary Size
- 32,256
- Release Date
- 2023-10-28
- License
- Other
Get Started
HuggingFace
How Much VRAM Does Deepseek Coder 33B Base Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 15.0 GB | 18.6 GB | 14.17 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 15.4 GB | 19.1 GB | 14.59 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 17.1 GB | 20.7 GB | 16.25 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 17.5 GB | 21.1 GB | 16.67 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 20.8 GB | 24.5 GB | 20.01 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 24.6 GB | 28.2 GB | 23.76 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 28.3 GB | 32.0 GB | 27.51 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 34.2 GB | 37.8 GB | 33.34 GB | 8-bit quantization, near-lossless |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run Deepseek Coder 33B Base?
Q4_K_M · 20.8 GBDeepseek Coder 33B Base (Q4_K_M) requires 20.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 28+ GB is recommended. Using the full 16K context window can add up to 3.6 GB, bringing total usage to 24.5 GB. 7 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroom
Which Devices Can Run Deepseek Coder 33B Base?
Q4_K_M · 20.8 GB41 devices with unified memory can run Deepseek Coder 33B Base, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightWhere to Download Deepseek Coder 33B Base
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Benchmarks
Benchmark details →Related Models
Frequently Asked Questions
- How much VRAM does Deepseek Coder 33B Base need?
Deepseek Coder 33B Base requires 20.8 GB of VRAM at Q4_K_M, or 67.5 GB at BF16. Full 16K context adds up to 3.6 GB (24.5 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 33.3B × 4.8 bits ÷ 8 = 20 GB
KV Cache + Overhead ≈ 0.8 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 4.5 GB (at full 16K context)
VRAM usage by quantization
Q4_K_M20.8 GBQ4_K_M + full context24.5 GB- Can NVIDIA GeForce RTX 4090 run Deepseek Coder 33B Base?
Yes, at Q5_K_S (23.7 GB) or lower. Higher quantizations like Q5_K_M (24.6 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for Deepseek Coder 33B Base?
For Deepseek Coder 33B Base, Q4_K_M (20.8 GB) offers the best balance of quality and VRAM usage. Q5_0 (21.7 GB) provides better quality if you have the VRAM. The smallest option is IQ3_XS at 14.6 GB.
VRAM requirement by quantization
IQ3_XS14.6 GBIQ3_M15.8 GBIQ4_XS18.7 GBQ4_K_M ★20.8 GBQ5_K_S23.7 GBBF1667.5 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Deepseek Coder 33B Base on a Mac?
Deepseek Coder 33B Base requires at least 14.6 GB at IQ3_XS, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Deepseek Coder 33B Base locally?
Yes — Deepseek Coder 33B Base can run locally on consumer hardware. At Q4_K_M quantization it needs 20.8 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Deepseek Coder 33B Base?
At Q4_K_M, Deepseek Coder 33B Base can reach ~230 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~32 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 ÷ 20.8 × 0.65 = ~250 tok/s
Estimated speed at Q4_K_M (20.8 GB)
~250 tok/s~32 tok/s~250 tok/s~230 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Deepseek Coder 33B Base?
At Q4_K_M, the download is about 20.01 GB. The full-precision BF16 version is 66.69 GB. The smallest option (IQ3_XS) is 13.75 GB.
- Which GPUs can run Deepseek Coder 33B Base?
7 consumer GPUs can run Deepseek Coder 33B Base at Q4_K_M (20.8 GB). Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090. 1 GPU have plenty of headroom for comfortable inference.
- Which devices can run Deepseek Coder 33B Base?
41 devices with unified memory can run Deepseek Coder 33B Base at Q4_K_M (20.8 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (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.