Qwen2.5-0.5B-Instruct Q4_K_M

qwen2.5-0.5b-instruct-q4_k_m.gguf · 0.49 GB

SHA-256 · 74a4da8c9fdbcd15bd1f6d01d621410d31c6fc00986f5eb687824e7b93d7a9db491400032 bytes

1 independent contributor · 1 report

ARM64 virtual CPU; physical model not exposed · 4.10194 GB RAM

Exploration

llama.cpp · b3991 (fc83a9e) · CPU (ARM64) · General chat · Load the exact GGUF in llama.cpp and confirm a short completion. · 2026-10-03

From ARM64 virtual CPU; physical model not exposed · 4.10194 GB RAM. Other hardware.

MeasurementsNot enough data

OutcomesWorked 1 of 1 reports

Report typeManual reports

Comparable groups

ARM64 virtual CPU; physical model not exposed · 4.10194 GB RAM

llama.cpp · b3991 (fc83a9e) · CPU (ARM64) · General chat · Load the exact GGUF in llama.cpp and confirm a short completion. · 1 contributor · 1 report

2026-10-03

Individual reports

Load the exact GGUF in llama.cpp and confirm a short completion.

Worked · operator reproduced · 2026-10-03

File identity

SHA-256 confirms the bytes, not file safety.

Quantization / quantizerQ4_K_M · Qwen

Identity methodtrusted checksum verified

Source revision9217f5db79a29953eb74d5343926648285ec7e67

LicenseApache-2.0 · approved

License evidenceThe Qwen base-model and GGUF cards declare Apache-2.0, and the pinned GGUF repository includes its LICENSE file: https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct and https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct-GGUF/blob/9217f5db79a29953eb74d5343926648285ec7e67/LICENSE. Local smoke listing only; resyn.cloud does not host the weights.

Reviewed byLocal MVP smoke test · 2026-10-03

llama.cpp

b3991 (fc83a9e) · CPU (ARM64)

GPU layers0

Threads2

Configured context512 tokens

More settings

{
  "batch_settings": {},
  "cache_settings": {
    "run_state": "fresh"
  },
  "other_settings": {
    "purpose": "local smoke test; no benchmark metrics collected"
  }
}

No reviewed command available.

Downloads

Weights are not hosted here. A source URL does not guarantee safety or compatibility.

Upstream statusReported available · 2026-10-03 · HTTP 200

Check detailPinned Hugging Face file downloaded; byte length and LFS SHA-256 matched.