id: qwen3-coder-30b-a3b-instruct-q4_k_m
name: Qwen3 Coder 30B A3B Instruct GGUF Q4_K_M
type: gguf-model
task:
  - 1c
  - code
  - agentic-coding
  - repository-analysis
  - tool-use
language:
  - ru
  - en
source: huggingface
upstream_id: lmstudio-community/Qwen3-Coder-30B-A3B-Instruct-GGUF
upstream_url: https://huggingface.co/lmstudio-community/Qwen3-Coder-30B-A3B-Instruct-GGUF
license: apache-2.0
status: candidate
created_at: 2026-06-19
storage_path: /models/gguf/1c/qwen3-coder-30b-a3b-instruct-q4_k_m
filename: Qwen3-Coder-30B-A3B-Instruct-Q4_K_M.gguf
file_size_bytes: 18632186176
format: gguf
quantization: Q4_K_M
context_length: 262144
deployment_context_length: 32768
vram_required_gb: null
parameters: 30.5B total / 3.3B active
base_model: Qwen/Qwen3-Coder-30B-A3B-Instruct
adapter_for: null
datasets: []
eval_suites:
  - plugins/1c/evals/smoke.yaml
deployment:
  target: docker-gpu.cin.su
  runtime: llama.cpp
  served_model_name: qwen3-coder-1c-q4
  compose: core/deploy/docker-gpu/llama-cpp/compose.yaml
notes: "Best current candidate found for 1C/code experiments. Not 1C-specific, but strong for agentic coding, long context, repository-scale understanding, and tool workflows."