Downloads · 30 days
36
20% of all-time downloads
evomodel-1.9
aisyahsyihab/evomodel-1.9
evomodel-1.9 is a text generation model from aisyahsyihab. Use it when you need the model to write or continue text. It is set up for llama.cpp. The card lists the license as apache-2.0.
A fine-tune of a Qwen-3.5 9B model, in GGUF for llama.cpp.
All-time downloads
184
Public
Repo size
5.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf5.6 GB · 100%
At a glance
- Task
- Text Generation
- Library
- llama.cpp
- License
- apache-2.0
- Access
- Public
- Created
- Jul 13, 2026
- Updated
- Jul 13, 2026
- SHA
- e7d18555
Try a prompt
Model card
From the Hugging Face model README
evomodel-1.9
A fine-tune of a Qwen-3.5 9B model, in GGUF for llama.cpp.
Files
| File | Quant | Size |
|---|---|---|
evomodel-1.9c-ck845-Q8_0.gguf | Q8_0 | ~8.9 GB |
evomodel-1.9c-ck845-NVFP4.gguf | NVFP4 | ~5.7 GB |
evomodel-1.9c-ck845-Q4_K_M.gguf | Q4_K_M | ~5.2 GB |
For NVFP4 and Q4_K_M, token_embd and output are kept at Q8_0.
Details
| Architecture | Qwen-3.5 (9B) |
| Adapter | LoRA r=8, alpha=8, merged at scale 1.0 |
| Context | up to 262k |
Run
llama-server -m evomodel-1.9c-ck845-Q4_K_M.gguf \
-ngl 99 --jinja --reasoning on -c 32768 --host 0.0.0.0 --port 8080
Tool calls use the native <function=…> dialect inside <tool_call>; the serving
client parses the raw text (llama.cpp does not parse this dialect itself).
- Task
- Text Generation
- Library
- llama.cpp
- License
- apache-2.0
- Created
- Jul 13, 2026
- Updated
- Jul 13, 2026