39 lines
897 B
YAML
39 lines
897 B
YAML
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."
|