id: qwen3-14b-instruct-q6_k
name: Qwen3 14B Instruct GGUF Q6_K
type: gguf-model
task:
  - text
  - chat
  - summarization
  - code
  - tool-use
  - 1c-rag
language:
  - ru
  - en
  - multilingual
source: huggingface
upstream_id: Qwen/Qwen3-14B-GGUF
upstream_url: https://huggingface.co/Qwen/Qwen3-14B-GGUF
license: apache-2.0
status: candidate
created_at: 2026-06-19
storage_path: /models/gguf/text/qwen3-14b-instruct-q6_k
filename: Qwen3-14B-Q6_K.gguf
file_size_bytes: 12121937248
format: gguf
quantization: Q6_K
context_length: 40960
deployment_context_length: 16384
vram_required_gb: 16
parameters: 14.8B
base_model: Qwen/Qwen3-14B
adapter_for: null
datasets: []
eval_suites: []
deployment:
  target: docker-gpu.cin.su
  runtime: llama.cpp
  served_model_name: qwen3-14b-q6
notes: "Stronger general text/chat candidate than Qwen3 4B while still comfortable for a single RTX 4090 in GGUF Q6_K."