---

language:

• en
• zh
• multilingual

license: apache-2.0

base_model: ewinregirgojr/Qwen3.8-9B-Instruct-Turbo

pipeline_tag: text-generation

library_name: transformers

tags:

• qwen
• qwen3
• qwen3_5
• qwen3.8
• 9b
• 27b
• thinking
• reasoning
• reasoning-model
• instruct
• turbo
• gguf
• mlx
• mlx-lm
• ollama
• vllm
• sglang
• unsloth
• lmstudio
• jan
• llama.cpp
• apple-silicon
• imatrix
• exl2
• awq
• gptq
• lorp
• layer-pruning
• pruning
• compression
• coding
• conversational
• endpoints_compatible
• text-generation
• safetensors
• region:us
• arxiv:2605.27786
• arxiv:2403.03853
• llama-cpp
• gguf-my-repo

inference: false

model-index:

• name: Qwen3.8-9B-Instruct-Turbo

results:

- task:

type: text-generation

name: Text Generation

dataset:

name: MMLU

type: mmlu

metrics:

- type: accuracy

value: 75.8

name: Accuracy

- task:

type: text-generation

name: Math Reasoning

dataset:

name: GSM8K

type: gsm8k

metrics:

- type: accuracy

value: 79.1

name: Accuracy

- task:

type: text-generation

name: Code Generation

dataset:

name: HumanEval

type: humaneval

metrics:

- type: accuracy

value: 68.2

name: Accuracy

---

ecyas/Qwen3.8-9B-Instruct-Turbo-Q6_K-GGUF

This model was converted to GGUF format from ewinregirgojr/Qwen3.8-9B-Instruct-Turbo using llama.cpp via the ggml.ai's GGUF-my-repo space.

Refer to the original model card for more details on the model.

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 ecyas/Qwen3.8-9B-Instruct-Turbo-Q6_K-GGUF --hf-file qwen3.8-9b-instruct-turbo-q6_k.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo ecyas/Qwen3.8-9B-Instruct-Turbo-Q6_K-GGUF --hf-file qwen3.8-9b-instruct-turbo-q6_k.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 ecyas/Qwen3.8-9B-Instruct-Turbo-Q6_K-GGUF --hf-file qwen3.8-9b-instruct-turbo-q6_k.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo ecyas/Qwen3.8-9B-Instruct-Turbo-Q6_K-GGUF --hf-file qwen3.8-9b-instruct-turbo-q6_k.gguf -c 2048