DeepSeek Coder V2
DeepSeek Coder V2 open-source MoE code model. 16B active parameters with 236B total. Comparable to GPT-4-Turbo on code-specific tasks.
What DeepSeek Coder V2 is for
DeepSeek Coder V2 is trained for code. DeepSeek released it in 2024-05 with 2 sizes (16B, 236B), 128K of context and a DeepSeek License licence. Context length matters more here than for chat, because a coding assistant that cannot see the whole file is guessing. The catalogue records its strength as strong 16B code model with MoE efficiency, and it is the class of model an editor plugin such as Continue or Tabby points at.
Sizes and memory
The 16B needs about 10 GB of weights at Q4_K_M and the 236B about 140 GB, a spread of 130 GB across the family. The catalogue's default pick is 16B. Recommended VRAM adds roughly half again on top of the weights for the KV cache and the runtime.
| Size | Weights at Q4_K_M | Recommended VRAM | Smallest card in our guide that holds it |
|---|---|---|---|
| 16B | 10 GB | 15 GB | NVIDIA RTX 3060 12GB |
| 236B | 140 GB | 210 GB | Apple M3 Ultra |
Hardware that runs DeepSeek Coder V2
18 of the 19 cards in our hardware guide hold at least one size of DeepSeek Coder V2 at Q4_K_M. The cheapest that does is the NVIDIA RTX 3060 12GB at about $250, running the 16B.
The largest size any of them holds is the 236B at 140 GB, on the Apple M3 Ultra (192 GB at 800 GB/s). Bandwidth, not capacity, sets the speed once a size fits, so a card further down the list with faster memory will generate more tokens per second on the same weights than a larger, slower one.
What people use it for
The catalogue lists 3 recorded uses for DeepSeek Coder V2: code, completion, code agents. It is tagged code, MoE, completion.
Where DeepSeek Coder V2 sits in the DeepSeek family
Our catalogue holds 4 DeepSeek entries. Ordered by release date, DeepSeek Coder V2 (2024-05) is the 2nd of them, and DeepSeek R1 (2025-01) is newer.
It ships under the DeepSeek License, which is neither a standard open-source licence nor a closed one. Read the terms before shipping anything commercial on top of it.
Context window: 128K
128K tokens is roughly 96,000 words at the usual ratio, which is a small repository or a whole book. Two cautions come with a window this size: the KV cache at full length can rival the weights for memory, and models rarely use the far end of their advertised context as well as they use the near end. Treat it as headroom, not as a promise.
How to run DeepSeek Coder V2 locally
Our catalogue does not record registry tags, so look the current tag up in the Ollama library or on Hugging Face before pasting these. The commands below are the shape of the workflow, not a copy-and-paste recipe.
Option 1: Ollama (simplest)
# find the tag for DeepSeek Coder V2 at ollama.com/library
ollama run <tag>Option 2: Mullama (production)
mullama pull <tag>
mullama run <tag>Option 3: llama.cpp (CLI)
# download a GGUF from Hugging Face, searching for "DeepSeek Coder V2 GGUF"
./llama-cli -m model.Q4_K_M.gguf -p "Hello, AI!"Option 4: Python with Mullama or llama-cpp-python
from mullama import Model, Context
model = Model.load("model.Q4_K_M.gguf", n_gpu_layers=99)
ctx = Context(model, n_ctx=4096)
print(ctx.generate("Hello, AI!", 256))Sources
Model record from src/data/models.json (2026-06-29); card capacities from src/data/gpus.json (2026-06-29). Upstream: Curated from ollama.com/library + community benchmarks + paperswithcode + huggingface.