Anrn 12B R1 is a 12B dense, natively multimodal Gemma 4 derivative distributed as a byte-identical BF16 base plus a project LoRA adapter applied at a tested scale of 0.45. The release supports text, image, audio, and video inputs through the native Transformers service and includes a ready-to-run llama.cpp text deployment.
Release layout: this repository intentionally keeps the original BF16 base and the trained adapter separate rather than destructively merging them. The included launchers compose both parts at runtime.
Benchmark results
Anrn 12B R1 benchmark results
Benchmark
Anrn 12B R1
MMLU-Pro
74.2
GPQA Diamond
77.8
AIME 2026 (no tools)
69.6
LiveCodeBench v6
68.3
Codeforces Elo
1521
BigBench Extra Hard
48.2
Tau2 Average
63.2
MMMU Pro
62.1
MRCR v2 (128K)
42.6
The Anrn values above come from the project's August 2026 evaluation run. The comparison values shown in the chart are reproduced from the published benchmark results used by that report; values marked with ~ are approximate.
Model details
Field
Value
Architecture
Gemma 4 Unified, dense decoder-only multimodal model
Parameters
11.95B
Base model
google/gemma-4-12B-it
Native precision
BF16
Adaptation
LoRA, rank 8, alpha 16
Tested adapter scale
0.45
Native modalities
Text, image, audio, video input; text output
Tested service context
131,072 tokens
Model configuration maximum
262,144 positions
Languages
Multilingual; optimized project behavior in Chinese and English
Default prompt
Project constitution embedded in system_prompt.md
Repository structure
text
1model/ Original BF16 Gemma 4 12B weights and processor files
2adapter/ Anrn R1 PEFT/LoRA adapter
3llama-model/ Q5_K_M GGUF base, Q8_0 GGUF LoRA, and embedded chat template
4llama-runtime/ Verified Windows CUDA llama.cpp runtime
5assets/ Benchmark figure
6start.ps1 Native multimodal OpenAI-compatible service
7serve.py Native service implementation
8Start-Llama-Service.bat
9 One-click llama.cpp text Web UI
Quick start: native multimodal service
Requirements: Windows, Python, a recent CUDA-capable NVIDIA GPU, and PowerShell.
The launcher loads model/, mounts adapter/ at scale 0.45, injects system_prompt.md, uses PyTorch SDPA for long-context inference, and automatically offloads language layers to system memory when required. The tested configuration used approximately 14 GB of GPU memory.
OpenAI-compatible endpoint:
POST http://127.0.0.1:8091/v1/chat/completions
Example health check:
Invoke-RestMethod http://127.0.0.1:8091/health
Quick start: llama.cpp Web UI
On Windows, double-click:
Start-Llama-Service.bat
The bootstrap checks the bundled llama.cpp runtime and, if it is missing, downloads a matching official Windows CUDA/CPU build. It then starts the text Web UI with:
131,072-token context
LoRA scale 0.45
Flash Attention
Q8_0 K/V cache
the project system prompt embedded in the Jinja chat template
Web UI: http://127.0.0.1:8091
Use Stop-Llama-Service.bat to stop it. The llama.cpp route is text-only; use start.ps1 for native image, audio, and video inputs.
Prompt behavior
system_prompt.md contains the release's default project constitution. The native server injects it before caller-provided system content. A request may set:
{"use_default_system_prompt": false}
to disable the default prompt for that request. The llama.cpp prompt is embedded in llama-model/chat_template.prompt30k.jinja.
Verification
The release contains machine-readable verification artifacts covering:
native text, image, audio, and video loading
prompt hash and injection behavior
llama.cpp health, 128K context, and live LoRA scale
identity smoke tests
package checksums and rollback scripts
Primary records: verification.json, llama-bootstrap-verification.json, prompt30k-verification.json, and SHA256SUMS.txt.
Limitations
Benchmark scores are sensitive to prompt templates, decoding parameters, judge versions, and harness revisions.
The BF16 base is large; CPU offload improves accessibility but reduces generation speed.
The included llama.cpp path is an auxiliary quantized text deployment and does not expose the native multimodal input path.
Users should evaluate the model for their target language, domain, and deployment policy before production use.
