v2.2 · 2026-06-12

DeepSeek-Coder 6.7B Instruct

deepseek-coder-6.7b-instruct

CODE

DeepSeek-Coder 6.7B Instruct is a 6.7B code model profile for local AI planning. This page records provider, license, context, quantization, hardware-fit estimates, setup hints, source links, and caveats so readers do not choose a model by name alone.

PROVIDER

DeepSeek

FAMILY

DeepSeek-Coder

MODEL TYPE

code

PARAMETERS

6.7B

MODALITIES

text, code

ARCHITECTURE

Dense code-specialized transformer

CONTEXT WINDOW

16,000 tokens

TRAINING TOKENS

—

RELEASE DATE

2023

LICENSE & LINKS

DeepSeek Model License

MODEL CARD

huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct

HUGGING FACE

deepseek-ai/deepseek-coder-6.7b-instruct

GGUF REPOSITORIES

TheBloke/deepseek-coder-6.7B-instruct-GGUF community conversion

Community GGUF repository referenced by the June 2026 model research.

SETUP HINTS

OLLAMA

ollama run deepseek-coder:6.7b

LM STUDIO

Available according to the supplied June 2026 research; select a cited GGUF/MLX build and verify current app metadata before relying on hands-on setup guidance.

LLAMA.CPP

Use the cited GGUF repository (TheBloke/deepseek-coder-6.7B-instruct-GGUF) with current llama.cpp-compatible tooling.

QUANTIZATION FILE SIZES (GGUF)

Q4_K_M

4.08 GB

Q5_K_M

4.79 GB

Q8_0

7.16 GB

Quantization note: Q4_K_M for first local attempts unless a cited runtime recommends a different default.

RAM / VRAM ESTIMATES

MIN RAM

8 GB

COMFORTABLE RAM

16 GB

MIN VRAM

8 GB

COMFORTABLE VRAM

16 GB

These are conservative local-inference estimates, not official hardware requirements.

HARDWARE FIT

CPU only (no GPU)

limited

8 GB RAM

limited

16 GB RAM

comfortable

32 GB RAM

comfortable

8 GB VRAM

limited

12 GB VRAM

limited

24 GB VRAM

comfortable

Apple Silicon (unified memory)

comfortable

Hardware fit values are conservative local-inference estimates based on GGUF size plus runtime and KV-cache overhead. Actual requirements depend on context length, quantization, runtime, GPU offload, and other running apps.

BEST FOR

·Small local coding help, simple scripts, and older laptops with limited memory or GPUs available.

AVOID IF

·You need repository-scale editing, modern tool use, or strong reasoning beyond coding basics today locally.

CAVEATS

·Keep as a lightweight legacy entry, not the main DeepSeek coding recommendation.

·Coder-V2 Lite is stronger for modern code and math workflows.

·The model card notes refusal behavior for politically sensitive and non-computer-science prompts.

·Commercial-use status from the supplied research: Commercial use supported by DeepSeek model card; review model license terms.

·Beginner summary from supplied research: DeepSeek-Coder 6.7B Instruct is the lightweight legacy DeepSeek coding entry. It is easy to run, useful for autocomplete-style help and small scripts, but no longer represents DeepSeek’s best reasoning or agentic coding work in 2026.

SOURCE URLS

[source 1] [source 2] [source 3] [source 4]

FIELD EVIDENCE

licensehuggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct

parameterSizeBhuggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct

activeParametersBhuggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct

architecturehuggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct

contextWindowTokenshuggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct

modalitieshuggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct

releaseDatehuggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct

hfGgufReposhuggingface.co/TheBloke/deepseek-coder-6.7B-instruct-GGUF

q4FileSizeGbhuggingface.co/TheBloke/deepseek-coder-6.7B-instruct-GGUF