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.
Decent on a 24 GB GPU
Runs on 24 GB (Q4_K_M · ~32 tok/s · 8K)Macs from 24 GB (IQ3_M · ~14 tok/s)
Other
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Deepseek Coder 33B Base
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
ollama run deepseek-coder:33b-base-q4_K_MQ4_K_M · needs ~24.5 GB · 16K context
Download: deepseek-coder-33b-base.Q4_K_M.gguf19.94 GBTheBloke
Ways to runOther ways
each opens step-by-stepRun in cloud
Your own private copy · Q4_K_M · 32 GB GPU
- The easiest way to try this model
- Running in a few minutes, easy setup
- Chat right here or connect any app
$5+ bonus for new users
Runs on RTX 5090 (32 GB) (7 GB headroom) · Q4_K_M
- Generation speed
- ~56 tok/s
- generation speed
- Cost per 1M output tokens
- $2.47
- per 1M output tokens
How Much VRAM Does Deepseek Coder 33B Base Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 15.0 GB | — | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 16K context · ~44 tok/s | |
| 15.4 GB | — | 3-bit small — 3-bit small quantization | Fits: 16K context · ~43 tok/s | |
| 17.1 GB | — | 3-bit medium — 3-bit medium quantization | Fits: 16K context · ~38 tok/s | |
| 17.5 GB | — | 4-bit · legacy — 4-bit legacy quantization | Fits: 16K context · ~38 tok/s | |
| 20.8 GB | — | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 8K context · ~32 tok/s | |
| 24.6 GB | — | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Does not fit: needs 28.2 GB | |
| 28.3 GB | — | 6-bit, very good — 6-bit quantization, very good quality | Does not fit: needs 32 GB | |
| 34.2 GB | — | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 37.8 GB |
Selected Q4_K_M
4-bit medium quantization24.5GBat 16K context
- Weights
- 20.0 GB
- KV cache
- 4.2 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · fits up to 8K context · ~32 tok/s
≥50 tok/s needs ≥1.60 TB/s · RTX 5090 ~56
Which Hardware 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. 100 devices with unified memory can run Deepseek Coder 33B Base, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M1 Max (32 GB).
20 GB
Q4_K_M · best fit IQ3_M (19.5 GB)
1 GPU
RX 7900 XT~30Simulate output on RX 7900 XT32–40 GB
fits · 7.5 GB free · up to 16K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~56Simulate output on RTX 5090M5 Max36 GB~16Simulate output on Mac Studio M5 Max (36 GB)M532 GB~5Simulate output on MacBook Air 13" M5 (32 GB)Orin~6Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~4Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
How good is Deepseek Coder 33B Base?
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 4 boards that have results for this model, sorted by their weight in the llmrun Score; badges show who ran the test.
- MMLU
Epoch AI · Nov 2023Lab-reported
Lab-reported39.4%
#71/85 open
- GSM8K
Epoch AI · Nov 2023Lab-reported
Lab-reported35.4%
#39/62 open
- ARC Challenge
Epoch AI · Nov 2023Lab-reported
Lab-reported42.2%
#38/56 open
- WinoGrande
Epoch AI · Nov 2023Lab-reported
Lab-reported62.0%
#40/51 open
Alternatives to Deepseek Coder 33B Base
DeepSeek Coder family · 11 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Nanbeige4.3 33BNanbeige | — | 23.7 GB | ~32 | same size |
| Sage A1.5InternScience | — | 22 GB | ~151 | same size |
| MiniCPM V 4.7 35B A3BOpenBMB | — | 22.1 GB | ~169 | same size |
| Llm Jp 4.1 32B A3b Thinkingllm-jp | — | 20.1 GB | ~188 | same size |
| Llm Jp 4.1 33B Thinkingllm-jp | — | 22.5 GB | ~35 | same size |
| Agnes 3.0 FlashAgnes-AI | — | 22.1 GB | ~35 | same size |
Specifications
- 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
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)
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 ≈ 4.5 GB (at full 16K context)
VRAM usage by quantization
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
★ Recommended — best balance of quality and VRAM usage.
Can I run Deepseek Coder 33B Base on a Mac?
Yes — Mac Mini M5 Pro (24 GB) and 106 other Macs can run Deepseek Coder 33B Base, the smallest at IQ3_M. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 20.8 GB of usable unified memory (RAM minus macOS overhead), from Mac Studio M1 Max (32 GB).
Can I run Deepseek Coder 33B Base locally?
Yes — Deepseek Coder 33B Base can run locally on consumer hardware. 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)
Real-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. Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090. 1 GPU has plenty of headroom for comfortable inference.
Which devices can run Deepseek Coder 33B Base?
100 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, 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.