huggingface-local-models

What the source does

• FilesystemNone observedNo reads or writes in the source
• NetworkNone observedNo outbound calls in the source
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass.

Audit 0.4.1 · source sha 17538af01850 · 28 Oct 2026Report an issue or request a re-scan

• Publisherhuggingface GitHub organizationOwner of the repository this skill is read from
• Source folderhuggingface/skills/skills/huggingface-local-modelsThe exact folder we audited
• LicenceApache-2.0As the repository states it
• Commit pinned for this verdict17538af01850A new audit runs when the source changes
• Repository statusNot archivedLast push 5 days ago
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conversion, and OpenAI-compatible local…

---
name: huggingface-local-models
description: "Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conversion, and OpenAI-compatible local serving."
---

# Hugging Face Local Models

Search the Hugging Face Hub for llama.cpp-compatible GGUF repos, choose the right quant, and launch the model with `llama-cli` or `llama-server`.

## Default Workflow

1. Search the Hub with `apps=llama.cpp`.
2. Open `https://huggingface.co/<repo>?local-app=llama.cpp`.
3. Prefer the exact HF local-app snippet and quant recommendation when it is visible.
4. Confirm exact `.gguf` filenames with `https://huggingface.co/api/models/<repo>/tree/main?recursive=true`.
5. Launch with `llama-cli -hf <repo>:<QUANT>` or `llama-server -hf <repo>:<QUANT>`.
6. Fall back to `--hf-repo` plus `--hf-file` when the repo uses custom file naming.
7. Convert from Transformers weights only if the repo does not already expose GGUF files.

## Quick Start

### Install llama.cpp

```bash
brew install llama.cpp
winget install llama.cpp
```

```bash
git clone https://github.com/ggml-org/llama.cpp
cd llama.cpp
make
```

### Authenticate for gated repos

```bash
hf auth login
```

### Search the Hub

```text
https://huggingface.co/models?apps=llama.cpp&sort=trending
https://huggingface.co/models?search=Qwen3.6&apps=llama.cpp&sort=trending
https://huggingface.co/models?search=<term>&apps=llama.cpp&num_parameters=min:0,max:24B&sort=trending
```

### Run directly from the Hub

```bash
llama-cli -hf unsloth/Qwen3.6-35B-A3B-GGUF:UD-Q4_K_M
llama-server -hf unsloth/Qwen3.6-35B-A3B-GGUF:UD-Q4_K_M
```

### Run an exact GGUF file

```bash
llama-server \
    --hf-repo unsloth/Qwen3.6-35B-A3B-GGUF \
    --hf-file Qwen3.6-35B-A3B-UD-Q4_K_M.gguf \
    -c 4096
```

### Convert only when no GGUF is available

```bash
hf download <repo-without-gguf> --local-dir ./model-src
python convert_hf_to_gguf.py ./model-src \
    --outfile model-f16.gguf \
    --outtype f16
llama-quantize model-f16.gguf model-q4_k_m.gguf Q4_K_M
```

### Smoke test a local server

```bash
llama-server -hf unsloth/Qwen3.6-35B-A3B-GGUF:UD-Q4_K_M
```

```bash
curl http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer no-key" \
  -d '{
    "messages": [
      {"role": "user", "content": "Write a limerick about exception handling"}
    ]
  }'
```

## Quant Choice

- Prefer the exact quant that HF marks as compatible on the `?local-app=llama.cpp` page.
- Keep repo-native labels such as `UD-Q4_K_M` instead of normalizing them.
- Default to `Q4_K_M` unless the repo page or hardware profile suggests otherwise.
- Prefer `Q5_K_M` or `Q6_K` for code or technical workloads when memory allows.
- Consider `Q3_K_M`, `Q4_K_S`, or repo-specific `IQ` / `UD-*` variants for tighter RAM or VRAM budgets.
- Treat `mmproj-*.gguf` files as projector weights, not the main checkpoint.

## Load References

- Read [hub-discovery.md](references/hub-discovery.md) for URL-first workflows, model search, tree API extraction, and command reconstruction.
- Read [quantization.md](references/quantization.md) for format tables, model scaling, quality tradeoffs, and `imatrix`.
- Read [hardware.md](references/hardware.md) for Metal, CUDA, ROCm, or CPU build and acceleration details.

## Resources

- llama.cpp: `https://github.com/ggml-org/llama.cpp`
- Hugging Face GGUF + llama.cpp docs: `https://huggingface.co/docs/hub/gguf-llamacpp`
- Hugging Face Local Apps docs: `https://huggingface.co/docs/hub/main/local-apps`
- Hugging Face Local Agents docs: `https://huggingface.co/docs/hub/agents-local`
- GGUF converter Space: `https://huggingface.co/spaces/ggml-org/gguf-my-repo`

Excerpt, first 3,779 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

git clone https://github.com/ggml-org/llama.cpp

git clone https://github.com/huggingface/skills
git -C skills checkout 17538af01850

Works in

1. 2026-10-28
   ✓SAFE B 89 / 100

   first audit · source 17538af01850

Questions about huggingface-local-models

• github.com/huggingface/skills/tree/main/skills/huggingface-local — the audited source at commit 17538af01850 and every finding aboveObserved · 28 Oct 2026

Spotted something wrong? Report a correction · Methodology