Views
No views yet
| Run locally | Pool multiple machines | OpenAI-compatible | Package variant |
|---|---|---|---|
| Private inference on your hardware | Split layers across peers | Serve /v1/chat/completions locally | UD-Q4_K_XL layer package |
| Property | Value |
|---|---|
| Source model | unsloth/Inkling-Small-GGUF |
| Model id | unsloth/Inkling-Small-GGUF:UD-Q4_K_XL |
| Family | Inkling |
| Parameter scale | not recorded |
| Quantization | UD-Q4_K_XL |
| Layer count | 42 |
| Activation width | 4096 |
| Package size | 153.1 GB |
| Source file | UD-Q4_K_XL/Inkling-Small-UD-Q4_K_XL-00001-of-00005.gguf |
| Package repo | meshllm/Inkling-Small-UD-Q4_K_XL-layers |
| License | apache-2.0 from unsloth/Inkling-Small-GGUF |
1# Run this on each machine that should contribute memory/compute.
2mesh-llm serve --model "meshllm/Inkling-Small-UD-Q4_K_XL-layers" --split1# Check the mesh and discover the OpenAI-compatible model name.
2curl -s http://localhost:3131/api/status
3curl -s http://localhost:3131/v1/models1# Send an OpenAI-compatible chat request.
2curl -s http://localhost:3131/v1/chat/completions \
3 -H "Content-Type: application/json" \
4 -d '{
5 "model": "unsloth/Inkling-Small-GGUF:UD-Q4_K_XL",
6 "messages": [{"role": "user", "content": "Write a tiny hello-world function in Rust."}],
7 "max_tokens": 128
8 }'| Property | Value |
|---|---|
| Format | layer-package |
| Canonical source ref | unsloth/Inkling-Small-GGUF@1a19ef82883cb7b9c581b93c30ea252dabbf658d/UD-Q4_K_XL/Inkling-Small-UD-Q4_K_XL-00001-of-00005.gguf |
| Source revision | 1a19ef82883cb7b9c581b93c30ea252dabbf658d |
| Source SHA-256 | a51ac3f439198f2817219edd582be4b600c273be24e78cbd58ebff982d9f007e |
| Skippy ABI | 0.1.35 |
| Package manifest SHA-256 | edae4bf5fd239d88fc2d20fb9eef31f6f7ce45ca743e1292827bc2a26e5f50c0 |
| Artifact | Path | Contents | SHA-256 |
|---|---|---|---|
| Manifest | model-package.json | Package schema, source identity, checksums | edae4bf5fd239d88fc2d20fb9eef31f6f7ce45ca743e1292827bc2a26e5f50c0 |
| Metadata | shared/metadata.gguf | 1 tensors, 12.4 MB | a30882bd63c7d3509acbe80f89fa3af26d2ea768a48d16aa29b39d0c31c57a65 |
| Embeddings | shared/embeddings.gguf | 2 tensors, 846.7 MB | 5e25470fcee8342e220fcf4a9d580afe7b1bbcce3a6bf1173b528a7c20074a72 |
| Output head | shared/output.gguf | 3 tensors, 846.7 MB | 66187e4186cab8645b1353feecdaaed350372202998a95ef5bbf860d38bd9a9d |
| Transformer layers | layers/layer-*.gguf | 42 layer artifacts, 998 tensors, 150.9 GB | see model-package.json |
| Projector | projectors/mmproj-BF16.gguf | mmproj projector, 132.3 MB | 05d4475a956030be87b099865d6552a541a476db8cc3e266fcfa7c5a24846248 |
| Projector | projectors/mmproj-F16.gguf | mmproj projector, 132.3 MB | bf1e6afc9889151b3fee61119d3ee2cd224b59a1d881cdf87e33962f64aecc7e |
| Projector | projectors/mmproj-F32.gguf | mmproj projector, 264.5 MB | 653c88aab6699d65ecd45d82303a74a467309dcb8e837e0c9e18f394f4ee3def |
mesh-llm ref main.
Each artifact is checksummed as it is written, uploaded to this repository, and removed from the job workspace before the next artifact is produced.skippy-model-package write-package "/source/UD-Q4_K_XL/Inkling-Small-UD-Q4_K_XL-00001-of-00005.gguf" --out-dir "/tmp/meshllm-layer-job-meshllm_Inkling-Small-UD-Q4_K_XL-layers-193/package"