deepseek-ai / text-generation updated 2 years ago

deepseek-coder-6.7b-instruct

Name: deepseek-coder-6.7b-instruct
Author: deepseek-ai

Deepseek Coder is composed of a series of code language models, each trained from scratch on 2T tokens, with a composition of 87% code and 13% natural language in both English and Chinese. We provide various sizes of the code model, ranging from 1B to 33B versions. Each model is pre-trained on project-level code corpus by employing a window size of 16K and a extra fill-in-the-blank task, to support project-level code...

Params

6.7 B

Context

16,384

Downloads 30d

553 K

Likes

507

Licence: other Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 10 days

553 K467 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	bf16	13.5 GB	16.3 GB	✅ Runs comfortably
model.safetensors (bf16, full)	bf16 + 16K ctx	13.5 GB	17.4 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/deepseek-coder-6-7b-instruct
{
  "hf_id": "deepseek-ai/deepseek-coder-6.7b-instruct",
  "params_b": 6.74,
  "context_length": 16384,
  "license": { "id": "other", "commercial": "unknown" },
  "downloads_30d": 553010,
  "vram_estimates": [
    { "quant": "bf16", "gb": 16.3 }
  ],
  "updated_at": "2026-07-28T18:05:28Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture: LlamaForCausalLM
Parameters: 6.7 B
Tensor type: BF16
Context length: 16,384
Vocabulary: 32,256
Layers / heads: 32 / 32
Licence: other
First seen on the Hub: 2023-10-29
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

Base model and the most-downloaded derivatives in the catalog.

Derivative deepseek-coder-6.7B-instruct-AWQ TheBloke 159 K

Compare with

Qwen3-8B 16.3 M Qwen2.5-7B-Instruct 12.1 M Qwen3.6-35B-A3B-NVFP4 11.3 M Llama-3.1-8B-Instruct 8.0 M Qwen2.5-7B-Instruct-AWQ 4.6 M granite-4.1-8b 4.2 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB