Downloads · 30 days
16
15% of all-time downloads
SR2AM-v0.1-8B-Q8_0-GGUF
dusterbloom/SR2AM-v0.1-8B-Q8_0-GGUF
SR2AM-v0.1-8B-Q8_0-GGUF is a text generation model from dusterbloom. Use it when you need the model to write or continue text. It is set up for gguf. The card lists the license as apache-2.0.
Q80 GGUF quantization of sailing-lab/SR2AM-v0.1-8B.
All-time downloads
104
Public
Repo size
8.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf8.7 GB · 100%
At a glance
- Task
- Text Generation
- Library
- gguf
- License
- apache-2.0
- Access
- Public
- Created
- May 23, 2026
- Updated
- May 23, 2026
- SHA
- 00612814
Try a prompt
Base models
Model card
From the Hugging Face model README
SR2AM-v0.1-8B-Q8_0-GGUF
Q8_0 GGUF quantization of sailing-lab/SR2AM-v0.1-8B.
Details
- Base model: sailing-lab/SR2AM-v0.1-8B (Qwen3-8B SFT+GRPO finetune)
- Quantization: Q8_0 (direct from BF16 safetensors via
convert_hf_to_gguf.py --outtype q8_0) - File size: 8.2 GB
- Tool: llama.cpp
- License: Apache 2.0 (inherited from base)
Usage
llama-cli -m SR2AM-v0.1-8B-Q8_0.gguf -ngl 99 -c 4096 \
-p "Plan a short trip to Rome in 3 bullet points:"
llama-server -m SR2AM-v0.1-8B-Q8_0.gguf -ngl 99 -c 4096 --port 8080
Tested on RTX 3090: ~94 tok/s generation, ~620 tok/s prompt eval, 10.4 GB VRAM at 4K context.
- Task
- Text Generation
- Library
- gguf
- License
- apache-2.0
- Created
- May 23, 2026
- Updated
- May 23, 2026