39 lines
1.3 KiB
YAML
39 lines
1.3 KiB
YAML
id: devstral-small-2-24b-instruct-2512-q4_k_m
|
|
name: Devstral Small 2 24B Instruct 2512 GGUF Q4_K_M
|
|
type: gguf-model
|
|
task:
|
|
- 1c
|
|
- code
|
|
- agentic-coding
|
|
- text
|
|
- tool-use
|
|
language:
|
|
- ru
|
|
- en
|
|
source: huggingface
|
|
upstream_id: bartowski/mistralai_Devstral-Small-2-24B-Instruct-2512-GGUF
|
|
upstream_url: https://huggingface.co/bartowski/mistralai_Devstral-Small-2-24B-Instruct-2512-GGUF
|
|
license: apache-2.0
|
|
status: candidate
|
|
created_at: 2026-06-18
|
|
storage_path: /models/gguf/1c/devstral-small-2-24b-instruct-2512-q4_k_m
|
|
filename: mistralai_Devstral-Small-2-24B-Instruct-2512-Q4_K_M.gguf
|
|
file_size_bytes: 14334438272
|
|
format: gguf
|
|
quantization: Q4_K_M
|
|
context_length: null
|
|
deployment_context_length: 32768
|
|
vram_required_gb: null
|
|
parameters: 24B
|
|
base_model: mistralai/Devstral-Small-2-24B-Instruct-2512
|
|
adapter_for: null
|
|
datasets: []
|
|
eval_suites:
|
|
- plugins/1c/evals/smoke.yaml
|
|
deployment:
|
|
target: docker-gpu.cin.su
|
|
runtime: llama.cpp
|
|
served_model_name: devstral-1c-q4
|
|
compose: core/deploy/docker-gpu/llama-cpp/compose.yaml
|
|
notes: "GGUF Q4_K_M quant for 1C/code experiments. Loads on docker-gpu.cin.su with llama.cpp CUDA and uses GPU, but current llama.cpp server returns empty decoded content for chat/completion despite token generation. Runtime is experimental until a compatible template/runtime/quant is found."
|