Frontis-MA1-35B-GGUF
This repository is the official local-deployment derivative of
Frontis-MA1-35B. It contains one
Q4_K_M language-model file and the F16 multimodal projector required for image input with
llama.cpp.
Files
| File | Size | Purpose |
|---|
Frontis-MA1-35B-Q4_K_M.gguf | 19.71 GiB | Q4_K_M language model |
mmproj-Frontis-MA1-35B-F16.gguf | 857.62 MiB | F16 vision encoder/projector |
checksums.txt | — | SHA-256 integrity manifest |
Only this deployment combination is published intentionally. The canonical BF16 Transformers weights remain in the base repository. This GGUF derivative does not publish a separate MTP draft-model variant.
Text and code quickstart
Tested conversion and inference tool:
llama.cpp b9637, commit
aedb2a5e9ca3d4064148bbb919e0ddc0c1b70ab3.
1llama-cli \
2 -m ./Frontis-MA1-35B-Q4_K_M.gguf \
3 -ngl all \
4 -c 32768 \
5 -n 1024 \
6 -cnv -st --simple-io \
7 -p "Build a strong tabular classification baseline and explain the validation design."
Image quickstart
1llama-cli \
2 -m ./Frontis-MA1-35B-Q4_K_M.gguf \
3 -mm ./mmproj-Frontis-MA1-35B-F16.gguf \
4 --image ./example.jpg \
5 -ngl all \
6 -c 32768 \
7 -n 512 \
8 -cnv -st --simple-io \
9 -p "Describe the image and identify information relevant to an ML workflow."
Reduce -c when memory is limited. On systems that cannot offload all layers, set -ngl to a smaller value or let llama.cpp choose automatically.
Release validation
Both final files passed SHA-256 verification and complete GGUF structure reads (733 language-model tensors and 334 projector tensors). The release also passed two real llama-cli smokes with full GPU offload on one NVIDIA H200: text generation from the Q4 file, and image-conditioned generation using the Q4 file with the F16 projector. These checks validate the release artifacts and command paths; they are not consumer-hardware speed benchmarks.
Component and evaluation scope
- The language-model weights are the OpenMLE post-trained Frontis-MA1-35B weights.
- The vision encoder/projector is inherited unchanged from Qwen3.6-35B-A3B and converted to F16 GGUF.
- OpenMLE post-training and the reported evaluations are text/code-only; they do not establish improved or fully validated visual capability.
Q4_K_M is lossy. Use the BF16 repository when maximum fidelity or paper-result reproduction is required.- The paper's reported scores measure the canonical model with the OpenMLE-Evo harness, not GGUF one-shot generation.
Generated code may be incorrect or unsafe. Execute it only in an isolated environment with explicit resource limits.
Paper result
The canonical BF16 model reaches 60.61% Medal Average and 0.7647 Human Rank with OpenMLE-Evo on the official 22-task MLE-Bench Lite split, compared with 39.39% and 0.5828 for its base model under the same harness. With OpenMLE-Evo-Max, the complete BF16 model–harness system reaches 71.21% and 0.8126. These are BF16 system results, not GGUF one-shot scores.
License
Original Frontis-MA1 material is released under CC BY-NC 4.0 for attribution-required, non-commercial use. Commercial use is not granted. The upstream Qwen Apache License 2.0 notice is preserved in LICENSE-UPSTREAM-APACHE-2.0 and NOTICE.
