-
netprojects/Qwen3.8-27B-hermes-adapted-GGUF
Image-Text-to-Text • 27B • Updated • 1 -
netprojects/Qwen3.8-27B-opencode-adapted-GGUF
Image-Text-to-Text • 27B • Updated • 172 • 1 -
netprojects/Qwen3.8-27B-pi-adapted-GGUF
Image-Text-to-Text • 27B • Updated • 335 • 6 -
netprojects/Nemotron-3.5-Rerank-8B-GGUF
Text Ranking • 8B • Updated • 986 • 1
AI & ML interests
On-device and local LLMs on Apple Silicon (MLX), small calibrated decision models, fact-checking and content quality for long-running websites, and open-source tooling for small teams.
Recent Activity
NetProjects
Open models, ready to run on Apple Silicon.
We convert and test open models for MLX (and GGUF for llama.cpp), so they run locally on a Mac with no cloud and no API keys. We check every build against the original model before it goes up, and we publish speed numbers from real hardware (MacBook Pro M5 Max, 128 GB).
Models
| Family | Builds | What it's for |
|---|---|---|
| NVIDIA Nemotron Dory 1.0 4B | bf16 · 8-bit · NVFP4 4-bit | Looped reasoning LM from NVIDIA Nemotron Labs |
| Tencent DSpine drafter for Qwen3.8-27B | drafter | Speculative decoding for Qwen3.8-27B: same output, 2.0x faster on 4-bit, 2.9x on 8-bit, 4.3x on bf16, and 2x or more with 33k-token prompts |
| NVIDIA Nemotron 3.5 Embed / Rerank | Embed-1B bf16 · 8-bit — Embed-8B 8-bit · 4-bit — Rerank-8B 8-bit · 4-bit · GGUF | Retrieval: embeddings and reranking for text and page images (scores match NVIDIA's published ViDoRe v3 results) |
| H2O-Lightning 4B | q8 · q4 | Small calibrated decision model from H2O.ai (text and images, two-way reading, Box questions) |
| SenseNova-Loop-9B | bf16 · 8-bit · 6-bit (recommended) · 4-bit — Preview: 8-bit · 6-bit · 4-bit | Looped Qwen3.5-based model from SenseNova (layers 4–27 run twice, two-stream mHC): text + image input, MTP decoding ~1.7× faster, 512K context |
| Fastino GLiDE 27B | 8-bit · 4-bit | Calibrated decision model (choice / yes-no / score), midloop, full-attention reading |
| AutoTrust JEV-35B | 8-bit · 4-bit mixed · 3-bit mixed | AutoTrust decision and classification model |
| AutoTrust-JEV-27B v1.1 | 8-bit · 4-bit | Decision model with bidirectional prompt reading (custom loader included) |
| IBM Granite Switch 4.1 | 8B 8-bit · 4-bit — 30B 8-bit · 4-bit | IBM Granite with switchable chat, decision and guardian modes |
| NVIDIA Cosmos3-Edge reasoner | 8-bit · 6-bit | Vision-language reasoner from NVIDIA: text, image and video in, text out |
| NVIDIA Cosmos3-Edge video generator | 8-bit · bf16 | Video generator from NVIDIA: text or a first frame in, video out (text-to-video, image-to-video, text-to-image) |
| Qwen Concept 27B | bf16 · 8-bit · 6-bit (recommended) · 4-bit | Qwen3.8-27B edited by Concept Country to reach answers with less thinking; text and images |
| Laplace-1-Atlas | bf16 · 8-bit · 6-bit (recommended) · 4-bit · GGUF | Juneo Lab's 27B decision model: scores candidates in one forward pass; JevBench 91.8% (6-bit) |
| Laplace-1-Vector | bf16 · 8-bit · 6-bit (recommended) · 4-bit | Juneo Lab's 4B decision model: scores candidates in one forward pass; JevBench 79.2% (6-bit) |
| SenseNova-6.8-Code2Video | bf16 · 8-bit · 6-bit (recommended) · 4-bit | SenseNova's 27B agentic code-to-video model: writes, renders and reviews video as code; vision tower kept |
| Mage-VL-Cowork | bf16 · 8-bit · 6-bit (recommended) · 4-bit | Microsoft's 4B hybrid computer-use agent (GUI + bash tools); vision tower kept in bf16 |
| Qwen3.8-27B-pi-adapted | 6-bit (recommended) · 8-bit · 4-bit · 3-bit · 2.5-bit · bf16 · MLX adapter · GGUF | harness-hub's pi coding-agent LoRA merged into Qwen3.8-27B (Terminal-Bench 2.1 39.5% → 55.8% under pi, publisher's figures); thinking off, vision and MTP kept |
| Qwen3.8-27B-opencode-adapted | 6-bit (recommended) · 8-bit · 4-bit · 3-bit · bf16 · MLX adapter · GGUF | harness-hub's OpenCode coding-agent LoRA merged into Qwen3.8-27B (SWE-bench Pro hard-51 35.3% → 51.0% under OpenCode, publisher's figures); thinking off, vision and MTP kept |
| DaisyRose-27B | 6-bit (recommended) · 8-bit · 4-bit · 3-bit · 2.5-bit · bf16 | RadixArk's reinforcement-learned Qwen3.8-27B (Terminal Bench 4.1 5.6 → 12.0, publisher's figures); thinking model, vision and MTP kept |
| Qwen3.8-27B-hermes-adapted | 6-bit (recommended) · 8-bit · 4-bit · 3-bit · 2.5-bit · bf16 · MLX adapter · GGUF | harness-hub's Hermes Agent LoRA merged into Qwen3.8-27B (SWE-bench Pro hard-51 29.4% → 43.1% under Hermes Agent, publisher's figures); thinking off, vision and MTP kept |
| Arete-27B | 6-bit (recommended) · 8-bit · 4-bit · 3-bit · 2.5-bit · bf16 | Nous Research's fine-tune of Qwen3.8-27B for factual, direct answers on sensitive topics; vision kept and MTP; 2.5-bit build is text-only |
How we build
- Conversions use the standard
mlx-lm/mlx-vlmtools, orllama.cppfor GGUF builds; where a model needs custom code, the loader is open source on GitHub. - Each card says which upstream revision it was built from, how it was quantized and how it was checked, with speed and memory measured on an M5 Max.
- Licences follow the original model.
Code
- dory-mlx: the
doryarchitecture for MLX-LM - dspine-hybrid-mlx: Tencent DSpine speculative decoding for hybrid Qwen3.8-27B on MLX (exact linear-attention rollback, fast long prompts, adaptive verify length)
- nemotron-retrieval-mlx: Nemotron 3.5 Embed / Rerank with page images,
/v1/embeddingsand/v1/rerankserver - h2o-lightning-mlx: H2O-Lightning 4B with H2O's official shim
- sensenova-loop-mlx: SenseNova-Loop-9B for MLX-LM (looped layers and two-stream mHC)
- glide-mlx: Fastino GLiDE 27B,
/v1/systemoneserver - autotrust-jev35b-mlx and autotrust-jev27b-mlx: AutoTrust JEV decision engines
- granite-switch-mlx: Granite Switch 4.1.1 support for MLX-LM
- cosmos3-edge-mlx: NVIDIA Cosmos3-Edge for MLX: the reasoner, with an OpenAI-compatible server for text, images and video, and the video generator
All builds: MLX collection and GGUF collection.
Also
We also work on small calibrated decision models, fact-checking and content quality for long-running websites, and open-source tooling for small teams.
Spotted a problem or want a model converted? Open a discussion on any model page.
-
netprojects/Qwen3.8-27B-hermes-adapted-MLX-6bit
Image-Text-to-Text • 28B • Updated -
netprojects/Qwen3.8-27B-hermes-adapted-MLX-8bit
Image-Text-to-Text • 28B • Updated -
netprojects/Qwen3.8-27B-hermes-adapted-MLX-4bit
Image-Text-to-Text • 28B • Updated -
netprojects/Qwen3.8-27B-hermes-adapted-MLX-3bit
Image-Text-to-Text • 28B • Updated • 1
-
netprojects/Qwen3.8-27B-hermes-adapted-GGUF
Image-Text-to-Text • 27B • Updated • 1 -
netprojects/Qwen3.8-27B-opencode-adapted-GGUF
Image-Text-to-Text • 27B • Updated • 172 • 1 -
netprojects/Qwen3.8-27B-pi-adapted-GGUF
Image-Text-to-Text • 27B • Updated • 335 • 6 -
netprojects/Nemotron-3.5-Rerank-8B-GGUF
Text Ranking • 8B • Updated • 986 • 1
-
netprojects/Qwen3.8-27B-hermes-adapted-MLX-6bit
Image-Text-to-Text • 28B • Updated -
netprojects/Qwen3.8-27B-hermes-adapted-MLX-8bit
Image-Text-to-Text • 28B • Updated -
netprojects/Qwen3.8-27B-hermes-adapted-MLX-4bit
Image-Text-to-Text • 28B • Updated -
netprojects/Qwen3.8-27B-hermes-adapted-MLX-3bit
Image-Text-to-Text • 28B • Updated • 1