Instructions to use bartowski/Llama-3-Orca-1.0-8B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bartowski/Llama-3-Orca-1.0-8B-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="bartowski/Llama-3-Orca-1.0-8B-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("bartowski/Llama-3-Orca-1.0-8B-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use bartowski/Llama-3-Orca-1.0-8B-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf bartowski/Llama-3-Orca-1.0-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bartowski/Llama-3-Orca-1.0-8B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf bartowski/Llama-3-Orca-1.0-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bartowski/Llama-3-Orca-1.0-8B-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf bartowski/Llama-3-Orca-1.0-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf bartowski/Llama-3-Orca-1.0-8B-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf bartowski/Llama-3-Orca-1.0-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf bartowski/Llama-3-Orca-1.0-8B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/bartowski/Llama-3-Orca-1.0-8B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use bartowski/Llama-3-Orca-1.0-8B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bartowski/Llama-3-Orca-1.0-8B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bartowski/Llama-3-Orca-1.0-8B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bartowski/Llama-3-Orca-1.0-8B-GGUF:Q4_K_M

SGLang

How to use bartowski/Llama-3-Orca-1.0-8B-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "bartowski/Llama-3-Orca-1.0-8B-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bartowski/Llama-3-Orca-1.0-8B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "bartowski/Llama-3-Orca-1.0-8B-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bartowski/Llama-3-Orca-1.0-8B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use bartowski/Llama-3-Orca-1.0-8B-GGUF with Ollama:
```
ollama run hf.co/bartowski/Llama-3-Orca-1.0-8B-GGUF:Q4_K_M
```

Unsloth Studio

How to use bartowski/Llama-3-Orca-1.0-8B-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for bartowski/Llama-3-Orca-1.0-8B-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for bartowski/Llama-3-Orca-1.0-8B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for bartowski/Llama-3-Orca-1.0-8B-GGUF to start chatting

Docker Model Runner
How to use bartowski/Llama-3-Orca-1.0-8B-GGUF with Docker Model Runner:
```
docker model run hf.co/bartowski/Llama-3-Orca-1.0-8B-GGUF:Q4_K_M
```

Lemonade

How to use bartowski/Llama-3-Orca-1.0-8B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bartowski/Llama-3-Orca-1.0-8B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Llama-3-Orca-1.0-8B-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

bartowski commited on Apr 21, 2024

Commit

d3f6fad

verified ·

1 Parent(s): c829f7f

Llamacpp quants

Browse files

Files changed (25) hide show

.gitattributes +23 -0
Llama-3-Orca-1.0-8B-IQ1_M.gguf +3 -0
Llama-3-Orca-1.0-8B-IQ1_S.gguf +3 -0
Llama-3-Orca-1.0-8B-IQ2_M.gguf +3 -0
Llama-3-Orca-1.0-8B-IQ2_S.gguf +3 -0
Llama-3-Orca-1.0-8B-IQ2_XS.gguf +3 -0
Llama-3-Orca-1.0-8B-IQ2_XXS.gguf +3 -0
Llama-3-Orca-1.0-8B-IQ3_M.gguf +3 -0
Llama-3-Orca-1.0-8B-IQ3_S.gguf +3 -0
Llama-3-Orca-1.0-8B-IQ3_XS.gguf +3 -0
Llama-3-Orca-1.0-8B-IQ3_XXS.gguf +3 -0
Llama-3-Orca-1.0-8B-IQ4_NL.gguf +3 -0
Llama-3-Orca-1.0-8B-IQ4_XS.gguf +3 -0
Llama-3-Orca-1.0-8B-Q2_K.gguf +3 -0
Llama-3-Orca-1.0-8B-Q3_K_L.gguf +3 -0
Llama-3-Orca-1.0-8B-Q3_K_M.gguf +3 -0
Llama-3-Orca-1.0-8B-Q3_K_S.gguf +3 -0
Llama-3-Orca-1.0-8B-Q4_K_M.gguf +3 -0
Llama-3-Orca-1.0-8B-Q4_K_S.gguf +3 -0
Llama-3-Orca-1.0-8B-Q5_K_M.gguf +3 -0
Llama-3-Orca-1.0-8B-Q5_K_S.gguf +3 -0
Llama-3-Orca-1.0-8B-Q6_K.gguf +3 -0
Llama-3-Orca-1.0-8B-Q8_0.gguf +3 -0
Llama-3-Orca-1.0-8B.imatrix +3 -0
README.md +84 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,26 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Llama-3-Orca-1.0-8B-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Orca-1.0-8B-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Orca-1.0-8B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Orca-1.0-8B-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Orca-1.0-8B-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Orca-1.0-8B-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Orca-1.0-8B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Orca-1.0-8B-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Orca-1.0-8B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Orca-1.0-8B-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Orca-1.0-8B-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Orca-1.0-8B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Orca-1.0-8B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Orca-1.0-8B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Orca-1.0-8B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Orca-1.0-8B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Orca-1.0-8B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Orca-1.0-8B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Orca-1.0-8B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Orca-1.0-8B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Orca-1.0-8B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Orca-1.0-8B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Orca-1.0-8B.imatrix filter=lfs diff=lfs merge=lfs -text

Llama-3-Orca-1.0-8B-IQ1_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1c23d974b3d210df1f535b24c31c6df87955089d4fba9ce3da4eab85cd218a93
+size 2161971712

Llama-3-Orca-1.0-8B-IQ1_S.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:62bc56b0e2c416e98ae44ec5abd7b65531be0b476b070dd23d7a35ea5e6def85
+size 2019627520

Llama-3-Orca-1.0-8B-IQ2_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8735ace8bdd370e029282e91d04628d61259ddd63391e2d75f399ae8d287c999
+size 2948280832

Llama-3-Orca-1.0-8B-IQ2_S.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e50970c5e14eb913dccdc3c742644339671444cf7df49fc499a5cf1cce2e7d55
+size 2758488576

Llama-3-Orca-1.0-8B-IQ2_XS.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:44d3442fa4de2e2c64fd3d407e6afc6b48d390034130fa87496aab070010d834
+size 2605781504

Llama-3-Orca-1.0-8B-IQ2_XXS.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:4f533a3c74c6840e3fdee60e03d41c5050f0f31f0227a93cff3184a61aed98b7
+size 2399212032

Llama-3-Orca-1.0-8B-IQ3_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8187be013d65ee6ec8d608c3166f82215c28735b95932395f509abad5b557490
+size 3784823296

Llama-3-Orca-1.0-8B-IQ3_S.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d1a765917504f3e3f915acc2d4b3c34888a0fa783af4db4920251dd8d8942835
+size 3682324992

Llama-3-Orca-1.0-8B-IQ3_XS.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:72aa2cd226532407ca22845ed79efc6354254dfb6161a98af02b88c0a2f69401
+size 3518747136

Llama-3-Orca-1.0-8B-IQ3_XXS.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:6542ce6012815db7c44cb6c2a78edee9af7323e8aecc89ce630db2de7ed0dbea
+size 3274912256

Llama-3-Orca-1.0-8B-IQ4_NL.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:68477dc5cf2902782bd093a65201fb51f09d58420a86117a72b9de6402ffed2a
+size 4677988864

Llama-3-Orca-1.0-8B-IQ4_XS.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:fcaf8ae805bcab78f79ffff587d86102e0ea9115fd22ddc00663eab3a162cfd0
+size 4447662592

Llama-3-Orca-1.0-8B-Q2_K.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:0da5632194733e05f3b9e801a5ee80a9ca52b9e741af69cd23b9482a9c29526c
+size 3179131392

Llama-3-Orca-1.0-8B-Q3_K_L.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ccc3f3b0da964f8fae64162c6231171018a77f026fd717d64b7c61ef77995700
+size 4321956352

Llama-3-Orca-1.0-8B-Q3_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:7b63756581dd8905eea3c19c75b5e28062860c4d3c50f420d90dea157fe77fd0
+size 4018917888

Llama-3-Orca-1.0-8B-Q3_K_S.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:66a377baea58ebfdba06d23c44aa937d39e68a68774f89ef2c3d7a51901fc9f1
+size 3664499200

Llama-3-Orca-1.0-8B-Q4_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:76fac33da4c0d7fb144eee943cbc64dfa769aeb6cf8ff7a3e530031f669c0b00
+size 4920734208

Llama-3-Orca-1.0-8B-Q4_K_S.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:05c47c8df59e9f963b956ba8278649da3e6acf5b1718ee5da626ab7de2863e18
+size 4692668928

Llama-3-Orca-1.0-8B-Q5_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c74c9a68e8956a99815ece56e545f91123bec9479261489e3200a71495a64734
+size 5732987392

Llama-3-Orca-1.0-8B-Q5_K_S.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1520215ca901d8b5eff97988eccbc8ea63590bbd7644debae760ab6a79e8b786
+size 5599293952

Llama-3-Orca-1.0-8B-Q6_K.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5d8ef6e2950fb75df7a0c68b00a0ece57bf8a082722fc68fee002f221b92da90
+size 6596006400

Llama-3-Orca-1.0-8B-Q8_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:286cad61bb58948e6352fb1d7a74fe48bc90c75ede256143e6226ab37454066e
+size 8540770816

Llama-3-Orca-1.0-8B.imatrix ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:db818aae1f2f5e131895efa2d81e54f02f3e4ac55b6bd7a78c642f76c180742b
+size 4988126

README.md ADDED Viewed

	@@ -0,0 +1,84 @@

+---
+library_name: transformers
+license: other
+datasets:
+- Open-Orca/SlimOrca-Dedup
+- jondurbin/airoboros-3.2
+- microsoft/orca-math-word-problems-200k
+- m-a-p/Code-Feedback
+- MaziyarPanahi/WizardLM_evol_instruct_V2_196k
+quantized_by: bartowski
+pipeline_tag: text-generation
+---
+## Llamacpp iMatrix Quantizations of Llama-3-Orca-1.0-8B
+Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/experimental">experimental</a> for quantization.
+Original model: https://huggingface.co/Locutusque/Llama-3-Orca-1.0-8B
+All quants made using imatrix option with dataset provided by Kalomaze [here](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384)
+## Prompt format
+```
+<|im_start|>system
+{system_prompt}<|im_end|>
+<|im_start|>user
+{prompt}<|im_end|>
+<|im_start|>assistant
+```
+## Download a file (not the whole branch) from below:
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [Llama-3-Orca-1.0-8B-Q8_0.gguf](https://huggingface.co/bartowski/Llama-3-Orca-1.0-8B-GGUF/blob/main/Llama-3-Orca-1.0-8B-Q8_0.gguf) | Q8_0 | 8.54GB | Extremely high quality, generally unneeded but max available quant. |
+| [Llama-3-Orca-1.0-8B-Q6_K.gguf](https://huggingface.co/bartowski/Llama-3-Orca-1.0-8B-GGUF/blob/main/Llama-3-Orca-1.0-8B-Q6_K.gguf) | Q6_K | 6.59GB | Very high quality, near perfect, *recommended*. |
+| [Llama-3-Orca-1.0-8B-Q5_K_M.gguf](https://huggingface.co/bartowski/Llama-3-Orca-1.0-8B-GGUF/blob/main/Llama-3-Orca-1.0-8B-Q5_K_M.gguf) | Q5_K_M | 5.73GB | High quality, *recommended*. |
+| [Llama-3-Orca-1.0-8B-Q5_K_S.gguf](https://huggingface.co/bartowski/Llama-3-Orca-1.0-8B-GGUF/blob/main/Llama-3-Orca-1.0-8B-Q5_K_S.gguf) | Q5_K_S | 5.59GB | High quality, *recommended*. |
+| [Llama-3-Orca-1.0-8B-Q4_K_M.gguf](https://huggingface.co/bartowski/Llama-3-Orca-1.0-8B-GGUF/blob/main/Llama-3-Orca-1.0-8B-Q4_K_M.gguf) | Q4_K_M | 4.92GB | Good quality, uses about 4.83 bits per weight, *recommended*. |
+| [Llama-3-Orca-1.0-8B-Q4_K_S.gguf](https://huggingface.co/bartowski/Llama-3-Orca-1.0-8B-GGUF/blob/main/Llama-3-Orca-1.0-8B-Q4_K_S.gguf) | Q4_K_S | 4.69GB | Slightly lower quality with more space savings, *recommended*. |
+| [Llama-3-Orca-1.0-8B-IQ4_NL.gguf](https://huggingface.co/bartowski/Llama-3-Orca-1.0-8B-GGUF/blob/main/Llama-3-Orca-1.0-8B-IQ4_NL.gguf) | IQ4_NL | 4.67GB | Decent quality, slightly smaller than Q4_K_S with similar performance *recommended*. |
+| [Llama-3-Orca-1.0-8B-IQ4_XS.gguf](https://huggingface.co/bartowski/Llama-3-Orca-1.0-8B-GGUF/blob/main/Llama-3-Orca-1.0-8B-IQ4_XS.gguf) | IQ4_XS | 4.44GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
+| [Llama-3-Orca-1.0-8B-Q3_K_L.gguf](https://huggingface.co/bartowski/Llama-3-Orca-1.0-8B-GGUF/blob/main/Llama-3-Orca-1.0-8B-Q3_K_L.gguf) | Q3_K_L | 4.32GB | Lower quality but usable, good for low RAM availability. |
+| [Llama-3-Orca-1.0-8B-Q3_K_M.gguf](https://huggingface.co/bartowski/Llama-3-Orca-1.0-8B-GGUF/blob/main/Llama-3-Orca-1.0-8B-Q3_K_M.gguf) | Q3_K_M | 4.01GB | Even lower quality. |
+| [Llama-3-Orca-1.0-8B-IQ3_M.gguf](https://huggingface.co/bartowski/Llama-3-Orca-1.0-8B-GGUF/blob/main/Llama-3-Orca-1.0-8B-IQ3_M.gguf) | IQ3_M | 3.78GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
+| [Llama-3-Orca-1.0-8B-IQ3_S.gguf](https://huggingface.co/bartowski/Llama-3-Orca-1.0-8B-GGUF/blob/main/Llama-3-Orca-1.0-8B-IQ3_S.gguf) | IQ3_S | 3.68GB | Lower quality, new method with decent performance, recommended over Q3_K_S quant, same size with better performance. |
+| [Llama-3-Orca-1.0-8B-Q3_K_S.gguf](https://huggingface.co/bartowski/Llama-3-Orca-1.0-8B-GGUF/blob/main/Llama-3-Orca-1.0-8B-Q3_K_S.gguf) | Q3_K_S | 3.66GB | Low quality, not recommended. |
+| [Llama-3-Orca-1.0-8B-IQ3_XS.gguf](https://huggingface.co/bartowski/Llama-3-Orca-1.0-8B-GGUF/blob/main/Llama-3-Orca-1.0-8B-IQ3_XS.gguf) | IQ3_XS | 3.51GB | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
+| [Llama-3-Orca-1.0-8B-IQ3_XXS.gguf](https://huggingface.co/bartowski/Llama-3-Orca-1.0-8B-GGUF/blob/main/Llama-3-Orca-1.0-8B-IQ3_XXS.gguf) | IQ3_XXS | 3.27GB | Lower quality, new method with decent performance, comparable to Q3 quants. |
+| [Llama-3-Orca-1.0-8B-Q2_K.gguf](https://huggingface.co/bartowski/Llama-3-Orca-1.0-8B-GGUF/blob/main/Llama-3-Orca-1.0-8B-Q2_K.gguf) | Q2_K | 3.17GB | Very low quality but surprisingly usable. |
+| [Llama-3-Orca-1.0-8B-IQ2_M.gguf](https://huggingface.co/bartowski/Llama-3-Orca-1.0-8B-GGUF/blob/main/Llama-3-Orca-1.0-8B-IQ2_M.gguf) | IQ2_M | 2.94GB | Very low quality, uses SOTA techniques to also be surprisingly usable. |
+| [Llama-3-Orca-1.0-8B-IQ2_S.gguf](https://huggingface.co/bartowski/Llama-3-Orca-1.0-8B-GGUF/blob/main/Llama-3-Orca-1.0-8B-IQ2_S.gguf) | IQ2_S | 2.75GB | Very low quality, uses SOTA techniques to be usable. |
+| [Llama-3-Orca-1.0-8B-IQ2_XS.gguf](https://huggingface.co/bartowski/Llama-3-Orca-1.0-8B-GGUF/blob/main/Llama-3-Orca-1.0-8B-IQ2_XS.gguf) | IQ2_XS | 2.60GB | Very low quality, uses SOTA techniques to be usable. |
+| [Llama-3-Orca-1.0-8B-IQ2_XXS.gguf](https://huggingface.co/bartowski/Llama-3-Orca-1.0-8B-GGUF/blob/main/Llama-3-Orca-1.0-8B-IQ2_XXS.gguf) | IQ2_XXS | 2.39GB | Lower quality, uses SOTA techniques to be usable. |
+| [Llama-3-Orca-1.0-8B-IQ1_M.gguf](https://huggingface.co/bartowski/Llama-3-Orca-1.0-8B-GGUF/blob/main/Llama-3-Orca-1.0-8B-IQ1_M.gguf) | IQ1_M | 2.16GB | Extremely low quality, *not* recommended. |
+| [Llama-3-Orca-1.0-8B-IQ1_S.gguf](https://huggingface.co/bartowski/Llama-3-Orca-1.0-8B-GGUF/blob/main/Llama-3-Orca-1.0-8B-IQ1_S.gguf) | IQ1_S | 2.01GB | Extremely low quality, *not* recommended. |
+## Which file should I choose?
+A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
+The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
+If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
+If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
+Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
+If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
+If you want to get more into the weeds, you can check out this extremely useful feature chart:
+[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix)
+But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
+These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
+The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.
+Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski