Capability matrix
- Compute and format Q4_K_M · Ryzen Zen 5 bring-up.
- Local entry point Text REPL.
- Server Unverified for this artifact. Check for a service that accepts this artifact.
- Harness No recorded client task. Run one identified request, then a task with a checked result.
Choose the download
Publisher model card · CKE input files
Publisher task: text generation. CKE example: Q4_K_M GGUF. Use this artifact identifier:
hf://ggml-org/Laguna-XS-2.1-GGUF/Laguna-XS-2.1-Q4_K_M.gguf.
Get started
--chat-template auto --thinking-mode suppressed --temperature 0.0 for the shortest smoke
version/v8/scripts/cks-v8-run run \
hf://ggml-org/Laguna-XS-2.1-GGUF/Laguna-XS-2.1-Q4_K_M.gguf \
--thinking-mode suppressed --max-tokens 64 --temperature 0.0 \
--prompt 'Give me a short example.'What has actually run?
Coherent text; exact embedding/RMSNorm and near-exact router replay. 2,048 tokens.
CPU evidence. Ryzen Zen 5 bring-up; diagnostic llama.cpp oracle.
Performance. Ryzen Zen 5 bring-up run: approximately 20 tokens/s prefill and 14 tokens/s decode. ARM throughput for this exact artifact is unverified here. Benchmark evidence · 32K to 128K results
Can I fine-tune it?
Full-checkpoint training, LoRA and other PEFT methods: no verified CKE recipe for this exact checkpoint in the reviewed evidence. For a trainable starter, use the FP32 and adapter recipes.
Start an interactive session
Run from the CKE checkout. Type a question, then /exit to finish.
version/v8/scripts/cks-v8-run run \
hf://ggml-org/Laguna-XS-2.1-GGUF/Laguna-XS-2.1-Q4_K_M.gguf \
--chat-template auto --thinking-mode suppressed --max-tokens 128 --temperature 0Try the HTTP server
For a short plain-text request, install the server dependencies and use a separate build directory. This command is a starting configuration. The capability card above records the checks completed for this artifact. Larger tool prompts need the context and serving variant specified by their harness.
version/v8/scripts/cks-v8-run serve \
hf://ggml-org/Laguna-XS-2.1-GGUF/Laguna-XS-2.1-Q4_K_M.gguf \
--run "$HOME/cke-runs/laguna-xs-2-1-chat" \
--context-len 1024 --max-tokens 64 --model-name cke-local \
--host 127.0.0.1 --port 8080