TheBloke / text-generation updated 2 years ago

deepseek-coder-6.7B-instruct-AWQ

Chat & support: TheBloke's Discord server Want to contribute? TheBloke's Patreon page TheBloke's LLM work is generously supported by a grant from andreessen horowitz (a16z)

Params
6.7 B
Context
16,384
Downloads 30d
159 K
Likes
19
Licence: other Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 55 days
▲ 0 in the last 30 days (0.0%)
269 K159 K
Jul 28Aug 15Sep 2Sep 20

Can you run it?

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

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
model.safetensors i32 3.9 GB 5.8 GB ✅ Runs comfortably
model.safetensors (bf16, full) bf16 + 16K ctx 3.9 GB 6.8 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-awq
{
  "hf_id": "TheBloke/deepseek-coder-6.7B-instruct-AWQ",
  "params_b": 6.74,
  "context_length": 16384,
  "license": { "id": "other", "commercial": "unknown" },
  "downloads_30d": 159257,
  "vram_estimates": [
    { "quant": "i32", "gb": 5.8 }
  ],
  "updated_at": "2026-07-28T18:07:01Z"
}
est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture
LlamaForCausalLM
Parameters
6.7 B
Tensor type
I32
Context length
16,384
Vocabulary
32,256
Layers / heads
32 / 32
Licence
other
First seen on the Hub
2023-11-05
Base model
deepseek-coder-6.7b-instruct
Training datasets
undisclosed
Added to our catalog
2026-07-28

Family

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

Compare with any text-generation model