Instructions to use AlexKitipov/microsoft_Fara-7B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use AlexKitipov/microsoft_Fara-7B-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 AlexKitipov/microsoft_Fara-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AlexKitipov/microsoft_Fara-7B-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 AlexKitipov/microsoft_Fara-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AlexKitipov/microsoft_Fara-7B-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 AlexKitipov/microsoft_Fara-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf AlexKitipov/microsoft_Fara-7B-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 AlexKitipov/microsoft_Fara-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AlexKitipov/microsoft_Fara-7B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/AlexKitipov/microsoft_Fara-7B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use AlexKitipov/microsoft_Fara-7B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AlexKitipov/microsoft_Fara-7B-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": "AlexKitipov/microsoft_Fara-7B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/AlexKitipov/microsoft_Fara-7B-GGUF:Q4_K_M

Ollama
How to use AlexKitipov/microsoft_Fara-7B-GGUF with Ollama:
```
ollama run hf.co/AlexKitipov/microsoft_Fara-7B-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use AlexKitipov/microsoft_Fara-7B-GGUF with Docker Model Runner:
```
docker model run hf.co/AlexKitipov/microsoft_Fara-7B-GGUF:Q4_K_M
```

Lemonade

How to use AlexKitipov/microsoft_Fara-7B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AlexKitipov/microsoft_Fara-7B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.microsoft_Fara-7B-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

AlexKitipov

bartowski commited on May 31

Commit

520dc9d

0 Parent(s):

Duplicate from bartowski/microsoft_Fara-7B-GGUF

Browse files

Co-authored-by: Bartowski <bartowski@users.noreply.huggingface.co>

Files changed (29) hide show

.gitattributes +62 -0
README.md +171 -0
microsoft_Fara-7B-IQ2_M.gguf +3 -0
microsoft_Fara-7B-IQ3_M.gguf +3 -0
microsoft_Fara-7B-IQ3_XS.gguf +3 -0
microsoft_Fara-7B-IQ3_XXS.gguf +3 -0
microsoft_Fara-7B-IQ4_NL.gguf +3 -0
microsoft_Fara-7B-IQ4_XS.gguf +3 -0
microsoft_Fara-7B-Q2_K.gguf +3 -0
microsoft_Fara-7B-Q2_K_L.gguf +3 -0
microsoft_Fara-7B-Q3_K_L.gguf +3 -0
microsoft_Fara-7B-Q3_K_M.gguf +3 -0
microsoft_Fara-7B-Q3_K_S.gguf +3 -0
microsoft_Fara-7B-Q3_K_XL.gguf +3 -0
microsoft_Fara-7B-Q4_0.gguf +3 -0
microsoft_Fara-7B-Q4_1.gguf +3 -0
microsoft_Fara-7B-Q4_K_L.gguf +3 -0
microsoft_Fara-7B-Q4_K_M.gguf +3 -0
microsoft_Fara-7B-Q4_K_S.gguf +3 -0
microsoft_Fara-7B-Q5_K_L.gguf +3 -0
microsoft_Fara-7B-Q5_K_M.gguf +3 -0
microsoft_Fara-7B-Q5_K_S.gguf +3 -0
microsoft_Fara-7B-Q6_K.gguf +3 -0
microsoft_Fara-7B-Q6_K_L.gguf +3 -0
microsoft_Fara-7B-Q8_0.gguf +3 -0
microsoft_Fara-7B-bf16.gguf +3 -0
microsoft_Fara-7B-imatrix.gguf +3 -0
mmproj-microsoft_Fara-7B-bf16.gguf +3 -0
mmproj-microsoft_Fara-7B-f16.gguf +3 -0

.gitattributes ADDED Viewed

	@@ -0,0 +1,62 @@

+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+microsoft_Fara-7B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+microsoft_Fara-7B-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+microsoft_Fara-7B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+microsoft_Fara-7B-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+microsoft_Fara-7B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+microsoft_Fara-7B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+microsoft_Fara-7B-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+microsoft_Fara-7B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+microsoft_Fara-7B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+microsoft_Fara-7B-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+microsoft_Fara-7B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+microsoft_Fara-7B-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
+microsoft_Fara-7B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+microsoft_Fara-7B-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
+microsoft_Fara-7B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+microsoft_Fara-7B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+microsoft_Fara-7B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+microsoft_Fara-7B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+microsoft_Fara-7B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+microsoft_Fara-7B-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+microsoft_Fara-7B-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+microsoft_Fara-7B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+microsoft_Fara-7B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
+microsoft_Fara-7B-bf16.gguf filter=lfs diff=lfs merge=lfs -text
+microsoft_Fara-7B-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
+mmproj-microsoft_Fara-7B-f16.gguf filter=lfs diff=lfs merge=lfs -text
+mmproj-microsoft_Fara-7B-bf16.gguf filter=lfs diff=lfs merge=lfs -text

README.md ADDED Viewed

	@@ -0,0 +1,171 @@

+---
+quantized_by: bartowski
+pipeline_tag: image-text-to-text
+base_model: microsoft/Fara-7B
+license: mit
+base_model_relation: quantized
+---
+## Llamacpp imatrix Quantizations of Fara-7B by microsoft
+Using <a href="https://github.com/ggml-org/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggml-org/llama.cpp/releases/tag/b7127">b7127</a> for quantization.
+Original model: https://huggingface.co/microsoft/Fara-7B
+All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) combined with a subset of combined_all_small.parquet from Ed Addario [here](https://huggingface.co/datasets/eaddario/imatrix-calibration/blob/main/combined_all_small.parquet)
+Run them in [LM Studio](https://lmstudio.ai/)
+Run them directly with [llama.cpp](https://github.com/ggml-org/llama.cpp), or any other llama.cpp based project
+## 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 | Split | Description |
+| -------- | ---------- | --------- | ----- | ----------- |
+| [Fara-7B-bf16.gguf](https://huggingface.co/bartowski/microsoft_Fara-7B-GGUF/blob/main/microsoft_Fara-7B-bf16.gguf) | bf16 | 15.24GB | false | Full BF16 weights. |
+| [Fara-7B-Q8_0.gguf](https://huggingface.co/bartowski/microsoft_Fara-7B-GGUF/blob/main/microsoft_Fara-7B-Q8_0.gguf) | Q8_0 | 8.10GB | false | Extremely high quality, generally unneeded but max available quant. |
+| [Fara-7B-Q6_K_L.gguf](https://huggingface.co/bartowski/microsoft_Fara-7B-GGUF/blob/main/microsoft_Fara-7B-Q6_K_L.gguf) | Q6_K_L | 6.52GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
+| [Fara-7B-Q6_K.gguf](https://huggingface.co/bartowski/microsoft_Fara-7B-GGUF/blob/main/microsoft_Fara-7B-Q6_K.gguf) | Q6_K | 6.25GB | false | Very high quality, near perfect, *recommended*. |
+| [Fara-7B-Q5_K_L.gguf](https://huggingface.co/bartowski/microsoft_Fara-7B-GGUF/blob/main/microsoft_Fara-7B-Q5_K_L.gguf) | Q5_K_L | 5.78GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
+| [Fara-7B-Q5_K_M.gguf](https://huggingface.co/bartowski/microsoft_Fara-7B-GGUF/blob/main/microsoft_Fara-7B-Q5_K_M.gguf) | Q5_K_M | 5.44GB | false | High quality, *recommended*. |
+| [Fara-7B-Q5_K_S.gguf](https://huggingface.co/bartowski/microsoft_Fara-7B-GGUF/blob/main/microsoft_Fara-7B-Q5_K_S.gguf) | Q5_K_S | 5.32GB | false | High quality, *recommended*. |
+| [Fara-7B-Q4_K_L.gguf](https://huggingface.co/bartowski/microsoft_Fara-7B-GGUF/blob/main/microsoft_Fara-7B-Q4_K_L.gguf) | Q4_K_L | 5.09GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
+| [Fara-7B-Q4_1.gguf](https://huggingface.co/bartowski/microsoft_Fara-7B-GGUF/blob/main/microsoft_Fara-7B-Q4_1.gguf) | Q4_1 | 4.87GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
+| [Fara-7B-Q4_K_M.gguf](https://huggingface.co/bartowski/microsoft_Fara-7B-GGUF/blob/main/microsoft_Fara-7B-Q4_K_M.gguf) | Q4_K_M | 4.68GB | false | Good quality, default size for most use cases, *recommended*. |
+| [Fara-7B-Q3_K_XL.gguf](https://huggingface.co/bartowski/microsoft_Fara-7B-GGUF/blob/main/microsoft_Fara-7B-Q3_K_XL.gguf) | Q3_K_XL | 4.57GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
+| [Fara-7B-Q4_K_S.gguf](https://huggingface.co/bartowski/microsoft_Fara-7B-GGUF/blob/main/microsoft_Fara-7B-Q4_K_S.gguf) | Q4_K_S | 4.46GB | false | Slightly lower quality with more space savings, *recommended*. |
+| [Fara-7B-Q4_0.gguf](https://huggingface.co/bartowski/microsoft_Fara-7B-GGUF/blob/main/microsoft_Fara-7B-Q4_0.gguf) | Q4_0 | 4.44GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
+| [Fara-7B-IQ4_NL.gguf](https://huggingface.co/bartowski/microsoft_Fara-7B-GGUF/blob/main/microsoft_Fara-7B-IQ4_NL.gguf) | IQ4_NL | 4.44GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
+| [Fara-7B-IQ4_XS.gguf](https://huggingface.co/bartowski/microsoft_Fara-7B-GGUF/blob/main/microsoft_Fara-7B-IQ4_XS.gguf) | IQ4_XS | 4.22GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
+| [Fara-7B-Q3_K_L.gguf](https://huggingface.co/bartowski/microsoft_Fara-7B-GGUF/blob/main/microsoft_Fara-7B-Q3_K_L.gguf) | Q3_K_L | 4.09GB | false | Lower quality but usable, good for low RAM availability. |
+| [Fara-7B-Q3_K_M.gguf](https://huggingface.co/bartowski/microsoft_Fara-7B-GGUF/blob/main/microsoft_Fara-7B-Q3_K_M.gguf) | Q3_K_M | 3.81GB | false | Low quality. |
+| [Fara-7B-IQ3_M.gguf](https://huggingface.co/bartowski/microsoft_Fara-7B-GGUF/blob/main/microsoft_Fara-7B-IQ3_M.gguf) | IQ3_M | 3.57GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
+| [Fara-7B-Q2_K_L.gguf](https://huggingface.co/bartowski/microsoft_Fara-7B-GGUF/blob/main/microsoft_Fara-7B-Q2_K_L.gguf) | Q2_K_L | 3.55GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
+| [Fara-7B-Q3_K_S.gguf](https://huggingface.co/bartowski/microsoft_Fara-7B-GGUF/blob/main/microsoft_Fara-7B-Q3_K_S.gguf) | Q3_K_S | 3.49GB | false | Low quality, not recommended. |
+| [Fara-7B-IQ3_XS.gguf](https://huggingface.co/bartowski/microsoft_Fara-7B-GGUF/blob/main/microsoft_Fara-7B-IQ3_XS.gguf) | IQ3_XS | 3.35GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
+| [Fara-7B-IQ3_XXS.gguf](https://huggingface.co/bartowski/microsoft_Fara-7B-GGUF/blob/main/microsoft_Fara-7B-IQ3_XXS.gguf) | IQ3_XXS | 3.11GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
+| [Fara-7B-Q2_K.gguf](https://huggingface.co/bartowski/microsoft_Fara-7B-GGUF/blob/main/microsoft_Fara-7B-Q2_K.gguf) | Q2_K | 3.02GB | false | Very low quality but surprisingly usable. |
+| [Fara-7B-IQ2_M.gguf](https://huggingface.co/bartowski/microsoft_Fara-7B-GGUF/blob/main/microsoft_Fara-7B-IQ2_M.gguf) | IQ2_M | 2.78GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
+## Embed/output weights
+Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.
+## Downloading using huggingface-cli
+<details>
+  <summary>Click to view download instructions</summary>
+First, make sure you have hugginface-cli installed:
+```
+pip install -U "huggingface_hub[cli]"
+```
+Then, you can target the specific file you want:
+```
+huggingface-cli download bartowski/microsoft_Fara-7B-GGUF --include "microsoft_Fara-7B-Q4_K_M.gguf" --local-dir ./
+```
+If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
+```
+huggingface-cli download bartowski/microsoft_Fara-7B-GGUF --include "microsoft_Fara-7B-Q8_0/*" --local-dir ./
+```
+You can either specify a new local-dir (microsoft_Fara-7B-Q8_0) or download them all in place (./)
+</details>
+## ARM/AVX information
+Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass.
+Now, however, there is something called "online repacking" for weights. details in [this PR](https://github.com/ggml-org/llama.cpp/pull/9921). If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly.
+As of llama.cpp build [b4282](https://github.com/ggml-org/llama.cpp/releases/tag/b4282) you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0.
+Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to [this PR](https://github.com/ggml-org/llama.cpp/pull/10541) which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase.
+<details>
+  <summary>Click to view Q4_0_X_X information (deprecated</summary>
+I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking.
+<details>
+  <summary>Click to view benchmarks on an AVX2 system (EPYC7702)</summary>
+| model                          |       size |     params | backend    | threads |          test |                  t/s |  % (vs Q4_0)  |
+| ------------------------------ | ---------: | ---------: | ---------- | ------: | ------------: | -------------------: |-------------: |
+| qwen2 3B Q4_0                  |   1.70 GiB |     3.09 B | CPU        |      64 |         pp512 |        204.03 ± 1.03 |          100% |
+| qwen2 3B Q4_0                  |   1.70 GiB |     3.09 B | CPU        |      64 |        pp1024 |        282.92 ± 0.19 |          100% |
+| qwen2 3B Q4_0                  |   1.70 GiB |     3.09 B | CPU        |      64 |        pp2048 |        259.49 ± 0.44 |          100% |
+| qwen2 3B Q4_0                  |   1.70 GiB |     3.09 B | CPU        |      64 |         tg128 |         39.12 ± 0.27 |          100% |
+| qwen2 3B Q4_0                  |   1.70 GiB |     3.09 B | CPU        |      64 |         tg256 |         39.31 ± 0.69 |          100% |
+| qwen2 3B Q4_0                  |   1.70 GiB |     3.09 B | CPU        |      64 |         tg512 |         40.52 ± 0.03 |          100% |
+| qwen2 3B Q4_K_M                |   1.79 GiB |     3.09 B | CPU        |      64 |         pp512 |        301.02 ± 1.74 |          147% |
+| qwen2 3B Q4_K_M                |   1.79 GiB |     3.09 B | CPU        |      64 |        pp1024 |        287.23 ± 0.20 |          101% |
+| qwen2 3B Q4_K_M                |   1.79 GiB |     3.09 B | CPU        |      64 |        pp2048 |        262.77 ± 1.81 |          101% |
+| qwen2 3B Q4_K_M                |   1.79 GiB |     3.09 B | CPU        |      64 |         tg128 |         18.80 ± 0.99 |           48% |
+| qwen2 3B Q4_K_M                |   1.79 GiB |     3.09 B | CPU        |      64 |         tg256 |         24.46 ± 3.04 |           83% |
+| qwen2 3B Q4_K_M                |   1.79 GiB |     3.09 B | CPU        |      64 |         tg512 |         36.32 ± 3.59 |           90% |
+| qwen2 3B Q4_0_8_8              |   1.69 GiB |     3.09 B | CPU        |      64 |         pp512 |        271.71 ± 3.53 |          133% |
+| qwen2 3B Q4_0_8_8              |   1.69 GiB |     3.09 B | CPU        |      64 |        pp1024 |       279.86 ± 45.63 |          100% |
+| qwen2 3B Q4_0_8_8              |   1.69 GiB |     3.09 B | CPU        |      64 |        pp2048 |        320.77 ± 5.00 |          124% |
+| qwen2 3B Q4_0_8_8              |   1.69 GiB |     3.09 B | CPU        |      64 |         tg128 |         43.51 ± 0.05 |          111% |
+| qwen2 3B Q4_0_8_8              |   1.69 GiB |     3.09 B | CPU        |      64 |         tg256 |         43.35 ± 0.09 |          110% |
+| qwen2 3B Q4_0_8_8              |   1.69 GiB |     3.09 B | CPU        |      64 |         tg512 |         42.60 ± 0.31 |          105% |
+Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation
+</details>
+</details>
+## Which file should I choose?
+<details>
+  <summary>Click here for details</summary>
+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/ggml-org/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, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
+</details>
+## Credits
+Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset.
+Thank you ZeroWw for the inspiration to experiment with embed/output.
+Thank you to LM Studio for sponsoring my work.
+Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski

microsoft_Fara-7B-IQ2_M.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:746e945b7c121d9cd6794efadcf1269ea2846db0abd3cebb77d3c5d42c526644
+size 2780341024

microsoft_Fara-7B-IQ3_M.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:f76fc5df8b6cd8c96b91da1c572a834e3009adca5b466ea2aad07dd828472ee9
+size 3574010656

microsoft_Fara-7B-IQ3_XS.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:707fb656d4dafdbe67f6c0c311ef56317cb628d4fd6228b9a045b3f7a093d824
+size 3346254624

microsoft_Fara-7B-IQ3_XXS.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:e615f828a3b8f2b3bda0c998068243ea7b68837882ddf3e462aeb87f941163f1
+size 3114513184

microsoft_Fara-7B-IQ4_NL.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:3c2a2ab24130d30919df0b3599d9388a1bad79cb9d15a07662bb671d2e0ce599
+size 4437812000

microsoft_Fara-7B-IQ4_XS.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:d35f2b8b7ff6b2c268cbedcc9c1c3f71ff1633ff95d23c12ea59227f8152915c
+size 4218471200

microsoft_Fara-7B-Q2_K.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:8e817a513c80b33a5d102a1b8a594eb001315e8767cae358c4c3337637feb202
+size 3015938848

microsoft_Fara-7B-Q2_K_L.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:3b38ae22605a3bb3fd99449546543adaba37376770c332643a4f8b0831e1b828
+size 3548162848

microsoft_Fara-7B-Q3_K_L.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:f7013d3eabecb7ab0133b7ee51bb549849879fe3f86f55f12bbbc7a94a48a32f
+size 4088458016

microsoft_Fara-7B-Q3_K_M.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:2131706aa1e07a6e33db5f84bb11c6336c36ecb8997a67fe333b637edaa72a58
+size 3808389920

microsoft_Fara-7B-Q3_K_S.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:bfa65ad0100afa3fe909bdc5b1e949bbce7a032c531e91c327ca3dadb2e7d1ba
+size 3492367136

microsoft_Fara-7B-Q3_K_XL.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:76bf2f1a84b5bf5acac58d9e8d6523518eed3aaf2b3d3c535bb3b829bb2eadaa
+size 4565330720

microsoft_Fara-7B-Q4_0.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:823fe36e9984f909f017259335aa6217100cafe869889e4befcb684b158dec15
+size 4444119840

microsoft_Fara-7B-Q4_1.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:3380576a19ca1cff5143a3778ab43b8c6b0a79bacfd15abd98d2d7392278412b
+size 4873282336

microsoft_Fara-7B-Q4_K_L.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:3d07b7e3c01e0048fde6e4c6fd4f2343ee5b94eb9a432b62170a4a52e182db1d
+size 5087562528

microsoft_Fara-7B-Q4_K_M.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:4597788eca332076afeb8376d64627583e1b14e10ce2e92a4a6d8a742f48a896
+size 4683072288

microsoft_Fara-7B-Q4_K_S.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:b45c60348ce441d2ba126f4c20ca70286954ea8f72070dd9d2e8974aa398affa
+size 4457767712

microsoft_Fara-7B-Q5_K_L.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:4a17684fdc0ceed23c54e994107b62ed7422a6805afd9ded550883e6a626d325
+size 5781195552

microsoft_Fara-7B-Q5_K_M.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:50831887f117e3860c93640497e8b76aa8800ba5276449664b1c9f254ae94e0e
+size 5444829984

microsoft_Fara-7B-Q5_K_S.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:fcac7a915ee9bd5d47c31bfbc8929378a9fb1af5c0cee9bd63e8161d3bc7b9a4
+size 5315175200

microsoft_Fara-7B-Q6_K.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:d42eedc154752051610d72adc2e8a5594c1a8845b62e482ce9dc83f46a235360
+size 6254197536

microsoft_Fara-7B-Q6_K_L.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:f03e558e6dabe9a8fcba374488a185390cccb7dca6f6c5a21f02c1cf8496923b
+size 6518180640

microsoft_Fara-7B-Q8_0.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:d828a73c92219e98fc0a82e490375ab8d209699ba656f1b6359a80887ca10784
+size 8098523936

microsoft_Fara-7B-bf16.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:8a2e072c86dddb48ee97482507a0b36a5fc0353f05892808a11a6118d292bdd7
+size 15237851648

microsoft_Fara-7B-imatrix.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a4685905847a6de8d74040f77f39992e438bcc36b4027b759305a1615b15aac1
+size 4560352

mmproj-microsoft_Fara-7B-bf16.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:7779ca6d81d862a497904423618eda45fe00b903d3e831db40d061d9a739f901
+size 1357173472

mmproj-microsoft_Fara-7B-f16.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:148cc0a76f0fc5aa467f44a11e0a3d98f530df920f1a315384aafdc1d31ddc76
+size 1354162912