metadata

base_model: DavidAU/Qwen3-8B-64k-Context-2X-Medium
library_name: transformers
pipeline_tag: text-generation
tags:
  - 64k context
  - reasoning
  - thinking
  - qwen3
  - llama-cpp
  - gguf-my-repo

Triangle104/Qwen3-8B-64k-Context-2X-Medium-Q5_K_M-GGUF

This model was converted to GGUF format from DavidAU/Qwen3-8B-64k-Context-2X-Medium using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

Qwen3 - 8B set at 64k (65536) context by extended YARN.

By changing the maximum context (from 32k) to different values this changes:

reasoning
prose, sentence, and output
general performance (up or down, depending on use case)
longer and/or more detailed outputs, especially long form.

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/Qwen3-8B-64k-Context-2X-Medium-Q5_K_M-GGUF --hf-file qwen3-8b-64k-context-2x-medium-q5_k_m.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo Triangle104/Qwen3-8B-64k-Context-2X-Medium-Q5_K_M-GGUF --hf-file qwen3-8b-64k-context-2x-medium-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/Qwen3-8B-64k-Context-2X-Medium-Q5_K_M-GGUF --hf-file qwen3-8b-64k-context-2x-medium-q5_k_m.gguf -p "The meaning to life and the universe is"

./llama-server --hf-repo Triangle104/Qwen3-8B-64k-Context-2X-Medium-Q5_K_M-GGUF --hf-file qwen3-8b-64k-context-2x-medium-q5_k_m.gguf -c 2048