How to use from
llama.cpp
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf yotisstudios/RaifuWars-Riko-B4-9B:Q8_0
# Run inference directly in the terminal:
llama cli -hf yotisstudios/RaifuWars-Riko-B4-9B:Q8_0
Install from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf yotisstudios/RaifuWars-Riko-B4-9B:Q8_0
# Run inference directly in the terminal:
llama cli -hf yotisstudios/RaifuWars-Riko-B4-9B:Q8_0
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf yotisstudios/RaifuWars-Riko-B4-9B:Q8_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf yotisstudios/RaifuWars-Riko-B4-9B:Q8_0
Use Docker
docker model run hf.co/yotisstudios/RaifuWars-Riko-B4-9B:Q8_0
Quick Links

Raifu Wars โ€” Riko narrator, B4-9B (merged)

The voice of Riko Ricochet, an AI VTuber who plays Raifu Wars live and talks through her own match: what she is doing and why, what the other players just did, and chat between turns.

This is B4-9B with RaifuWars-Riko-B4-9B-LoRA merged in. Training, data and limitations are on the LoRA's page.

Files

file use
model-0000*-of-00004.safetensors + configs bf16, transformers (Qwen3_5ForConditionalGeneration); B4-9B's MTP head is included unchanged
RaifuWars-Riko-B4-9B-Q8_0.gguf llama.cpp, Q8_0, without the MTP head; fits a 16 GB card with room for context
llama-server -m RaifuWars-Riko-B4-9B-Q8_0.gguf -c 24576 -ngl 99 -fa on --jinja

Use it with thinking off, as it was trained and measured.

Does merging cost anything?

For an earlier B4-9B adapter, merging and then quantizing to Q8_0 lost most of the gain, so this one was measured both ways. 838 held-out narrator prompts, two lines each (1,676 lines), seed 99; "good" means the line passed the rule checker and the judge.

narrator good hard fail judge flag judge score
B4-9B Q8_0 57.2% 16.0% 22.6% 3.63
B4-9B Q8_0 + the f16 LoRA at runtime 92.1% 0.9% 3.9% 3.98
this model, Q8_0 GGUF 91.3% 0.5% 4.2% 3.98

The 0.8-point gap between the last two is within noise at 1,676 lines.

On stream she currently runs the second row (B4-9B Q8_0 with the LoRA at runtime); this model is the same narrator as a single file.

Downloads last month
101
Safetensors
Model size
10B params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for yotisstudios/RaifuWars-Riko-B4-9B