DeepSeek Coder V2
Coding-focused MoE model with 21B active parameters out of 236B total. Supports 338 programming languages with strong performance across mainstream stacks (Python, TypeScript, Go, Rust, Java, C++) and competent results on niche languages where most open models falter.
The DeepSeek licence applies — commercial use permitted with some application restrictions.
- Parameters
- 236B
- Context length
- 128K
- Modality
- text
- Released
- 2024-06-17
Memory & hardware
- VRAM (fp16)
- 472 GB
- VRAM (Q4)
- 141.6 GB
- Recommended
- 4× A100 80GB or 2× H100
- Quantizations
- fp16, q8_0, q4_k_m
Benchmarks
Hosted inference pricing
USD per million tokens.
| Provider | Input | Output | |
|---|---|---|---|
| deepinfraCheapest | $0.14 | $0.28 |
Run it yourself
Drop-in commands for the three most common open-source inference paths. The Ollama tag is a best-effort match against the registry; verify the size variant before pulling.
vllm serve deepseek-ai/DeepSeek-Coder-V2-Instruct
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-Coder-V2-Instruct")
model = AutoModelForCausalLM.from_pretrained(
"deepseek-ai/DeepSeek-Coder-V2-Instruct", device_map="auto", torch_dtype="auto"
)deepseek-ai/DeepSeek-Coder-V2-Instruct Related models
Same family or similar size — useful when shopping around.
R1 reasoning capabilities distilled into a Llama 3.3 70B base. The most accessible way to run R1-class reasoning locally — fits on a single H100 in fp16 or on a 4090 at Q4. Inherits Llama 3's community licence (commercial use under 700M MAU). Great pick for production reasoning workloads where the full R1 is too expensive to host but o1/R1-style quality is required.
- Context
- 128K
- License
- llama-3
- VRAM Q4
- 42 GB
671B-parameter MoE model with 37B active per token. Trained for roughly $5.6M of compute — a landmark in cost-efficient frontier training. Frontier-class quality at a fraction of the cost of the closed proprietary frontier. The DeepSeek licence permits commercial use with limited restrictions on military and unlawful applications. Running V3 yourself requires serious hardware (8× H100 at fp8); most teams will use it via the DeepSeek API or providers like Together.
- Context
- 128K
- License
- deepseek
- VRAM Q4
- 402.6 GB
Reasoning model trained with reinforcement learning on top of DeepSeek V3-Base. MIT licence — even the weights are unrestricted, making R1 the most permissively-licensed frontier reasoning model. Generates long internal chains-of-thought before answering, trading latency for accuracy on math, code, and reasoning benchmarks. Distilled variants (e.g. R1 Distill Llama 70B) recover most of the quality at much smaller scales.
- Context
- 128K
- License
- mit
- VRAM Q4
- 402.6 GB
xAI's first open-weights release: a 314B-parameter mixture-of-experts model. Apache 2.0 licensed. Largely a research artefact at this size — most users will run smaller models for production — but useful as a permissively-licensed reference for MoE research.
- Context
- 8K
- License
- apache-2-0
- VRAM Q4
- 188.4 GB
Scaled-up Mixtral with 22B-parameter experts. ~39B active parameters out of 141B total. Strong long-context performance and competitive coding scores. Apache 2.0 makes it attractive for self-hosting where the licence terms of Llama 3 are a non-starter.
- Context
- 66K
- License
- apache-2-0
- VRAM Q4
- 84.6 GB
NVIDIA's reward-modelling research vehicle. Trained primarily to be a synthetic-data-generation specialist rather than a chat-first model. Useful for teams building instruction-tuning datasets at scale.
- Context
- 4K
- License
- llama-3
- VRAM Q4
- 204 GB