Triangle104/Qwen3-Esper3-Reasoning-CODER-Instruct-12B-Brainstorm20x-Q5_K_M-GGUF

This model was converted to GGUF format from DavidAU/Qwen3-Esper3-Reasoning-CODER-Instruct-12B-Brainstorm20x using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

---

This model contains Brainstorm 20x, combined with ValiantLabs's 8B General / Coder (instruct model):

https://huggingface.co/ValiantLabs/Qwen3-8B-Esper3

Information on the 8B model below, followed by Brainstorm 20x adapter (by DavidAU) and then a complete help section for running LLM / AI models.

The Brainstorm adapter improves code generation, and unique code solving abilities.

This model requires:

• Jinja (embedded) or CHATML template
• Max context of 40k.

Settings used for testing (suggested):

• Temp .3 to .7
• Rep pen 1.05 to 1.1
• Topp .8 , minp .05
• Topk 20
• No system prompt.

FOR CODING:

Higher temps: .6 to .9 (even over 1) work better for more complex coding / especially with more restrictions.

This model will respond well to both detailed instructions and step by step refinement and additions to code.

As this is an instruct model, it will also benefit from a detailed system prompt too.

---

Use with llama.cpp

Install llama.cpp through brew (works on Mac and Linux)

brew install llama.cpp

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo Triangle104/Qwen3-Esper3-Reasoning-CODER-Instruct-12B-Brainstorm20x-Q5_K_M-GGUF --hf-file qwen3-esper3-reasoning-coder-instruct-12b-brainstorm20x-q5_k_m.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo Triangle104/Qwen3-Esper3-Reasoning-CODER-Instruct-12B-Brainstorm20x-Q5_K_M-GGUF --hf-file qwen3-esper3-reasoning-coder-instruct-12b-brainstorm20x-q5_k_m.gguf -c 2048

Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.

Step 1: Clone llama.cpp from GitHub.

git clone https://github.com/ggerganov/llama.cpp

Step 2: Move into the llama.cpp folder and build it with LLAMA_CURL=1 flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).

cd llama.cpp && LLAMA_CURL=1 make

Step 3: Run inference through the main binary.

./llama-cli --hf-repo Triangle104/Qwen3-Esper3-Reasoning-CODER-Instruct-12B-Brainstorm20x-Q5_K_M-GGUF --hf-file qwen3-esper3-reasoning-coder-instruct-12b-brainstorm20x-q5_k_m.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo Triangle104/Qwen3-Esper3-Reasoning-CODER-Instruct-12B-Brainstorm20x-Q5_K_M-GGUF --hf-file qwen3-esper3-reasoning-coder-instruct-12b-brainstorm20x-q5_k_m.gguf -c 2048