prithivMLmods/LevelField-GGUF overview
LevelField GGUF LevelField 1 https://huggingface.co/level ai/LevelField is the first open source large language model purpose built for non standard machining …
Runs locally from ~879.0 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| LevelField.BF16.gguf | GGUF | GGUF | 16.69 GB | Download |
| LevelField.Q3_K_L.gguf | GGUF | GGUF | 4.59 GB | Download |
| LevelField.Q3_K_M.gguf | GGUF | GGUF | 4.31 GB | Download |
| LevelField.Q3_K_S.gguf | GGUF | GGUF | 3.97 GB | Download |
| LevelField.Q4_0.gguf | GGUF | GGUF | 4.95 GB | Download |
| LevelField.Q4_K_M.gguf | GGUF | GGUF | 5.24 GB | Download |
| LevelField.Q4_K_S.gguf | GGUF | GGUF | 4.98 GB | Download |
| LevelField.Q5_0.gguf | GGUF | GGUF | 5.87 GB | Download |
| LevelField.Q5_K_M.gguf | GGUF | GGUF | 6.02 GB | Download |
| LevelField.Q5_K_S.gguf | GGUF | GGUF | 5.87 GB | Download |
| LevelField.mmproj-bf16.gguf | GGUF | BF16 | 879.0 MB | Download |
Model Details
| Model ID | prithivMLmods/LevelField-GGUF |
|---|---|
| Author | prithivMLmods |
| Pipeline | image-text-to-text |
| License | apache-2.0 |
| Base model | level-ai/LevelField |
| Last modified | 2026-09-10T10:16:06.000Z |
Model README
---
license: apache-2.0
base_model:
- level-ai/LevelField
library_name: transformers
tags:
- text-generation-inference
- llama-cpp
- manufacturing
- process-planning
- machining
- industrial-ai
- multimodal
- qwen3_5
language:
- en
- zh
pipeline_tag: image-text-to-text
---
LevelField-GGUF
> LevelField-1 is the first open-source large language model purpose-built for non-standard machining process planning, developed by Level AI (蓝沃AI) and built on Qwen3.5-9B, fine-tuned and reinforced with 100,000 manufacturing drawings and process sheets sourced from 16 factories, with data construction and result validation performed jointly by Level AI's engineering team and 36 process engineers averaging 20+ years of hands-on experience. Given a 2D manufacturing drawing (PDF or PNG), it interprets part geometry, dimensions and tolerances, surface roughness, and other technical specifications, then generates a complete machining process route with optimization suggestions, covering 18 common process types including turning, milling, drilling, grinding, casting, forging, heat treatment, and welding. In internal evaluation, its process reasoning achieved 95%+ alignment with decisions made by senior process engineers, and in pilot customer deployments it reduced process route drafting time by roughly 60%. The 9B-parameter model is released as merged BF16 safetensors weights (~20GB), deployable via vLLM (requiring at least one H100 GPU) with a Qwen3 reasoning parser, or tried directly through Level AI's hosted online demo, and is licensed under Apache 2.0 for free commercial use.
Model Files
File Name | Quant Type | File Size | File Link |
|-----------|------------|-----------|-----------|
| LevelField.BF16.gguf | BF16 | 17.9 GB | Download |
| LevelField.Q3_K_L.gguf | Q3_K_L | 4.93 GB | Download |
| LevelField.Q3_K_M.gguf | Q3_K_M | 4.62 GB | Download |
| LevelField.Q3_K_S.gguf | Q3_K_S | 4.26 GB | Download |
| LevelField.Q4_0.gguf | Q4_0 | 5.31 GB | Download |
| LevelField.Q4_K_M.gguf | Q4_K_M | 5.63 GB | Download |
| LevelField.Q4_K_S.gguf | Q4_K_S | 5.35 GB | Download |
| LevelField.Q5_0.gguf | Q5_0 | 6.31 GB | Download |
| LevelField.Q5_K_M.gguf | Q5_K_M | 6.47 GB | Download |
| LevelField.Q5_K_S.gguf | Q5_K_S | 6.31 GB | Download |
| LevelField.mmproj-bf16.gguf | mmproj-bf16 | 922 MB | Download |
llama.cpp
LLM inference in C/C++ — https://github.com/ggml-org/llama.cpp
Run prithivMLmods/LevelField-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models