---
language:
- en
- fr
- multilingual
license: apache-2.0
tags:
- gguf
- quantized
- mac
- apple-silicon
- local-inference
- worthdoing
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
quantized_by: worthdoing
pipeline_tag: text-generation
---

<p align="center">
  <img src="https://raw.githubusercontent.com/Worth-Doing/brand-assets/main/png/variants/04-horizontal.png" alt="worthdoing" width="400"/>
</p>
<p align="center"><strong>Author: Simon-Pierre Boucher</strong></p>

<p align="center">
  <img src="https://img.shields.io/badge/Format-GGUF-blue?style=for-the-badge" alt="GGUF"/>
  <img src="https://img.shields.io/badge/Params-1.1B-orange?style=for-the-badge" alt="Parameters"/>
  <img src="https://img.shields.io/badge/Platform-Apple_Silicon-black?style=for-the-badge&logo=apple" alt="Apple Silicon"/>
  <img src="https://img.shields.io/badge/License-Apache_2.0-green?style=for-the-badge" alt="License"/>
  <img src="https://img.shields.io/badge/Quantized_by-worthdoing-purple?style=for-the-badge" alt="worthdoing"/>
</p>
<p align="center">
  <img src="https://img.shields.io/badge/Q4__K__M-0.6_GB-brightgreen?style=flat-square" alt="Q4_K_M"/>
  <img src="https://img.shields.io/badge/Q5__K__M-0.7_GB-yellow?style=flat-square" alt="Q5_K_M"/>
  <img src="https://img.shields.io/badge/Q8__0-1.0_GB-red?style=flat-square" alt="Q8_0"/>
</p>

# TinyLlama-1.1B-Chat-v1.0 - GGUF Quantized by worthdoing

> Quantized for local Mac inference (Apple Silicon / Metal) by **worthdoing**

## About

This is a GGUF quantized version of [TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0), optimized for running locally on Apple Silicon Macs with `llama.cpp`, `Ollama`, or `LM Studio`.

- **Original model:** [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0)
- **Parameters:** 1.1B
- **Quantized by:** worthdoing
- **Pipeline:** corelm-model v1.0

## Description

Ultra-tiny Llama variant. Minimal resource usage for basic tasks.

## Available Quantizations

| File | Quant | BPW | Size | Use Case |
|------|-------|-----|------|----------|
| `tinyllama-1.1b-chat-v1.0-Q4_K_M-worthdoing.gguf` | Q4_K_M | 4.58 | ~0.6 GB | **Recommended** - Best quality/size ratio |
| `tinyllama-1.1b-chat-v1.0-Q5_K_M-worthdoing.gguf` | Q5_K_M | 5.33 | ~0.7 GB | Higher quality, still fast |
| `tinyllama-1.1b-chat-v1.0-Q8_0-worthdoing.gguf` | Q8_0 | 7.96 | ~1.0 GB | Near-original quality |

## How to Use

### With Ollama
```bash
# Create a Modelfile
cat > Modelfile <<'MODELEOF'
FROM ./tinyllama-1.1b-chat-v1.0-Q4_K_M-worthdoing.gguf
MODELEOF

ollama create tinyllama-1.1b-chat-v1.0 -f Modelfile
ollama run tinyllama-1.1b-chat-v1.0
```

### With llama.cpp
```bash
llama-cli -m tinyllama-1.1b-chat-v1.0-Q4_K_M-worthdoing.gguf -p "Your prompt here" -ngl 99
```

### With LM Studio
1. Download the GGUF file
2. Open LM Studio -> My Models -> Import
3. Select the GGUF file and start chatting

## Quantization Method

Our quantization pipeline (**corelm-model v1.0**) follows a rigorous multi-step process to ensure maximum quality and compatibility:

### Step 1 — Download & Validation
- Model weights are downloaded from HuggingFace Hub in **SafeTensors** format (`.safetensors`)
- Legacy formats (`.bin`, `.pt`) are excluded to ensure clean, verified weights
- Tokenizer, configuration, and all metadata are preserved

### Step 2 — Conversion to GGUF F16 Baseline
- The original model is converted to **GGUF format at FP16 precision** using `convert_hf_to_gguf.py` from [llama.cpp](https://github.com/ggml-org/llama.cpp)
- This lossless baseline preserves the full original model quality
- Architecture-specific tensors (attention, FFN, embeddings, MoE routing) are mapped to their GGUF equivalents

### Step 3 — K-Quant Quantization
- The F16 baseline is quantized using `llama-quantize` with **k-quant methods**
- K-quants use a mixed-precision approach: more important layers (attention, output) retain higher precision, while less sensitive layers (FFN) are compressed more aggressively
- Each quantization level offers a different quality/size tradeoff:

| Method | Bits per Weight | Strategy |
|--------|----------------|----------|
| **Q4_K_M** | ~4.58 bpw | Mixed 4/5-bit. Attention & output layers use Q5_K, FFN layers use Q4_K. Best balance of quality and size. |
| **Q5_K_M** | ~5.33 bpw | Mixed 5/6-bit. Attention & output layers use Q6_K, FFN layers use Q5_K. Higher quality with moderate size increase. |
| **Q8_0** | ~7.96 bpw | Uniform 8-bit. All layers quantized to 8-bit. Near-lossless quality, largest file size. |

### Step 4 — Metadata Injection
- Custom metadata is embedded directly in each GGUF file:
  - `general.quantized_by`: worthdoing
  - `general.quantization_version`: corelm-1.0
- This ensures full traceability and provenance of every quantized file

### Tools & Environment
- **llama.cpp**: Used for both conversion and quantization — the industry-standard open-source LLM inference engine
- **Target platform**: Apple Silicon Macs (M1/M2/M3/M4) with Metal GPU acceleration
- **Inference runtimes**: Compatible with `llama.cpp`, `Ollama`, `LM Studio`, `koboldcpp`, and any GGUF-compatible runtime

## Recommended Hardware

| Quant | Min RAM | Recommended |
|-------|---------|-------------|
| Q4_K_M | 4 GB | Mac with 8 GB+ RAM |
| Q5_K_M | 4 GB | Mac with 8 GB+ RAM |
| Q8_0 | 4 GB | Mac with 8 GB+ RAM |

## Tags

`general`, `ultra-lightweight`, `edge`

---

*Quantized with corelm-model pipeline by **worthdoing** on 2026-04-17*