Interesting Models
Models I've used myself.
Text Generation • 685B • Updated • 2.68M • • 1.45kNote My favorite model of all time.
google/gemma-4-31B-it
Image-Text-to-Text • 33B • Updated • 11.1M • • 3.07kNote My go-to model for a variety of tasks, like conversations / precise translation / roleplay. Really good vision and understands nuance and finer patterns that 26B-A4B doesn't pick up on.
google/gemma-4-26B-A4B-it
Image-Text-to-Text • 27B • Updated • 13.2M • • 1.2kNote A fantastic model for OCR tasks! Also usable for translations.
Qwen/Qwen3.6-35B-A3B
Image-Text-to-Text • 36B • Updated • 5.61M • • 2.26kNote My go-to programming agent. Very fast and very capable.
Qwen/Qwen3.6-27B
Image-Text-to-Text • 28B • Updated • 5.64M • • 1.82kNote While it's a tad slow for programming, it's a great planner and really useful for complex problems that Qwen3.6-35B-A3B can't solve due to MoE sparsity. Also nice for tool calling and websearch.
mradermacher/Qwen3-30B-A3B-Thinking-2507-Deepseek-v3.1-Distill-FP32-GGUF
31B • Updated • 95 • 4Note A distil of deepseek v3.1! It feels like an updated version of DeepSeek-R1-Distill-Qwen-32B.
mradermacher/Magistral-Small-2507-Rebased-Vision-i1-GGUF
24B • Updated • 1.52k • 1Note The model that gave me the most wholesome roleplay I've had locally.
Delta-Vector/Rei-24B-KTO
Text Generation • 24B • Updated • 51 • • 18Note My most used RP model, great at a wide range of topics.
Delta-Vector/Rei-V3-KTO-12B
12B • Updated • 74 • 22Note Great for SFW RPs, has a soft spot in my heart for being the first RP model I've ever used.
Delta-Vector/Hamanasu-Magnum-4B
5B • Updated • 11 • 4Note My first RP model on my laptop with only 8GB RAM and no VRAM.
tencent/HY-MT1.5-1.8B
Translation • 2B • Updated • 22.4k • 1.18kNote A very tiny and efficient translation model, runnable on 8GB RAM with no VRAM.
zerofata/G4-MeroMero-31B-gguf
31B • Updated • 7.9k • 19Note Awesome Gemma4 finetune.
-
Simplepotat/gemma-4-31b-it-qat-q4_0-assistant-gguf
Image-Text-to-Text • 0.5B • Updated • 8.02k • 9