Downloads · 30 days
47
7% of all-time downloads
QUEST-35B-RL-GGUF
lumbago-unfunny/QUEST-35B-RL-GGUF
QUEST-35B-RL-GGUF is a text generation model from lumbago-unfunny. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
Quantized GGUF files of osunlp/QUEST-35B-RL by OSU NLP Group — a 35B Qwen3.5-MoE model with linear attention.
All-time downloads
634
Public
Repo size
49.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf49.7 GB · 100%
At a glance
- Task
- Text Generation
- License
- apache-2.0
- Access
- Public
- Created
- Jun 27, 2026
- Updated
- Jun 29, 2026
- SHA
- 56e4d580
Try a prompt
Base models
Model card
From the Hugging Face model README
QUEST-35B-RL-GGUF
Quantized GGUF files of osunlp/QUEST-35B-RL by OSU NLP Group — a 35B Qwen3.5-MoE model with linear attention.
Model Details
| Property | Value |
|---|---|
| Architecture | Qwen3.5-MoE (Mixture of Experts) |
| Parameters | ~35B total |
| Hidden size | 2048 |
| Layers | 40 (linear attention + full attention hybrid) |
| Experts | 256 + 1 shared, 8 active per token |
| Context length | 262,144 tokens |
| Vocabulary | 248,320 |
| RoPE theta | 10,000,000 |
| Base model | osunlp/QUEST-35B-RL |
Available Quants
| File | Size | BPW | Description |
|---|---|---|---|
QUEST-35B-RL-Q6_K.gguf | 27 GB | 6.58 | High quality, recommended |
QUEST-35B-RL-Q4_K_M.gguf | 20 GB | 4.88 | Good quality, smaller footprint |
Usage
Compatible with llama.cpp, LM Studio, and any GGUF-compatible inference engine.
# llama.cpp
./llama-cli -m QUEST-35B-RL-Q6_K.gguf -ngl 999 -c 262144
# llama-server
./llama-server -m QUEST-35B-RL-Q6_K.gguf -ngl 999 -c 262144 --port 8080
Conversion
Converted from the original safetensors using llama.cpp convert_hf_to_gguf.py and quantized with llama-quantize.
- Task
- Text Generation
- License
- apache-2.0
- Languages
- en
- Created
- Jun 27, 2026
- Updated
- Jun 29, 2026