---

license: apache-2.0

base_model: lued/Qwen3.8-27B-INT8-W8A16-MTP

library_name: vllm

pipeline_tag: image-text-to-text

tags:

• qwen3_5
• qwen3.8
• compressed-tensors
• w8a16
• int8
• quantized
• vllm
• mtp
• speculative-decoding
• vision
• conversational
• llama-cpp
• gguf-my-repo

base_model_relation: quantized

---

jerkar/Qwen3.8-27B-INT8-W8A16-MTP-Q4_K_S-GGUF

This model was converted to GGUF format from lued/Qwen3.8-27B-INT8-W8A16-MTP 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 jerkar/Qwen3.8-27B-INT8-W8A16-MTP-Q4_K_S-GGUF --hf-file qwen3.8-27b-int8-w8a16-mtp-q4_k_s.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo jerkar/Qwen3.8-27B-INT8-W8A16-MTP-Q4_K_S-GGUF --hf-file qwen3.8-27b-int8-w8a16-mtp-q4_k_s.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 jerkar/Qwen3.8-27B-INT8-W8A16-MTP-Q4_K_S-GGUF --hf-file qwen3.8-27b-int8-w8a16-mtp-q4_k_s.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo jerkar/Qwen3.8-27B-INT8-W8A16-MTP-Q4_K_S-GGUF --hf-file qwen3.8-27b-int8-w8a16-mtp-q4_k_s.gguf -c 2048