Downloads · 30 days
40
24% of all-time downloads
Gazal-R1-32B-GRPO-preview-GGUF
TachyHealth/Gazal-R1-32B-GRPO-preview-GGUF
Gazal-R1-32B-GRPO-preview-GGUF is a machine learning model from TachyHealth. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
GGUF conversions of TachyHealth/Gazal-R1-32B-GRPO-preview, produced with llama.cpp's converthftogguf.py and llama-quantize.
All-time downloads
168
Public
Repo size
54.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf54.6 GB · 100%
At a glance
- Access
- Public
- Created
- Aug 18, 2026
- Updated
- Aug 18, 2026
- SHA
- 588059f5
Base models
Model card
From the Hugging Face model README
Gazal-R1-32B-GRPO-preview — GGUF quantized
GGUF conversions of TachyHealth/Gazal-R1-32B-GRPO-preview, produced with llama.cpp's
convert_hf_to_gguf.py and llama-quantize.
| File | Quant | Notes |
|---|---|---|
Gazal-R1-32B-GRPO-preview-BF16.gguf | BF16 | Full-precision master GGUF, source for the quantized files below |
Gazal-R1-32B-GRPO-preview-Q8_0.gguf | Q8_0 (8-bit) | Near-lossless, ~half the size of BF16 |
Gazal-R1-32B-GRPO-preview-Q4_K_M.gguf | Q4_K_M (4-bit) | Smallest, some quality loss vs full precision |
Usage (llama.cpp)
./llama-cli -m Gazal-R1-32B-GRPO-preview-Q4_K_M.gguf -p "Your prompt here"
Also compatible with any GGUF-supporting runtime (Ollama, LM Studio, text-generation-webui, koboldcpp, etc.).
- Created
- Aug 18, 2026
- Updated
- Aug 18, 2026