Capability matrix
- Compute and format Q4_K_M · Commodity x86 nightly lanes.
- Local entry point Text REPL.
- Server Local HTTP pass. Qwen2 answered via Responses on the cached 1K bundle.
- Harness Tool workflow unverified. Test a client and a complete tool round trip.
Choose the download
Publisher model card · CKE input files
Publisher task: text generation. CKE example: Q4_K_M GGUF. Use this artifact identifier:
hf://Qwen/Qwen2-0.5B-Instruct-GGUF/qwen2-0_5b-instruct-q4_k_m.gguf.
Get started
--chat-template auto
version/v8/scripts/cks-v8-run run \
hf://Qwen/Qwen2-0.5B-Instruct-GGUF/qwen2-0_5b-instruct-q4_k_m.gguf \
--context-len 1024 --force-compile --force-convert \
--generate-visualizerWalk through a verified question and answer.
What has actually run?
Coherent GGUF end-to-end nightly lanes. 1,024 tokens where recorded.
CPU evidence. Commodity x86 nightly lanes; provider selected from detected ISA.
Performance. On the local Intel Core i7-1260P, a 26-token formatted prompt ran at 142.48 tokens/s and 24 decode steps at 29.33 tokens/s. Single cached-model observation. 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://Qwen/Qwen2-0.5B-Instruct-GGUF/qwen2-0_5b-instruct-q4_k_m.gguf \
--chat-template auto --max-tokens 128 --temperature 0