39 lines
1.2 KiB
YAML
39 lines
1.2 KiB
YAML
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."
|