Instructions to use mradermacher/KCOMP-MASH-QA-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mradermacher/KCOMP-MASH-QA-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mradermacher/KCOMP-MASH-QA-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use mradermacher/KCOMP-MASH-QA-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 mradermacher/KCOMP-MASH-QA-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mradermacher/KCOMP-MASH-QA-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 mradermacher/KCOMP-MASH-QA-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mradermacher/KCOMP-MASH-QA-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 mradermacher/KCOMP-MASH-QA-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mradermacher/KCOMP-MASH-QA-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 mradermacher/KCOMP-MASH-QA-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mradermacher/KCOMP-MASH-QA-GGUF:Q4_K_M

Use Docker

docker model run hf.co/mradermacher/KCOMP-MASH-QA-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use mradermacher/KCOMP-MASH-QA-GGUF with Ollama:
```
ollama run hf.co/mradermacher/KCOMP-MASH-QA-GGUF:Q4_K_M
```

Unsloth Studio

How to use mradermacher/KCOMP-MASH-QA-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 mradermacher/KCOMP-MASH-QA-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 mradermacher/KCOMP-MASH-QA-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mradermacher/KCOMP-MASH-QA-GGUF to start chatting

Docker Model Runner
How to use mradermacher/KCOMP-MASH-QA-GGUF with Docker Model Runner:
```
docker model run hf.co/mradermacher/KCOMP-MASH-QA-GGUF:Q4_K_M
```

Lemonade

How to use mradermacher/KCOMP-MASH-QA-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mradermacher/KCOMP-MASH-QA-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.KCOMP-MASH-QA-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

mradermacher commited on Jul 7, 2025

Commit

a4f2a06

verified ·

1 Parent(s): e214033

uploaded from kaos

Browse files

Files changed (13) hide show

.gitattributes +12 -0
KCOMP-MASH-QA.IQ4_XS.gguf +3 -0
KCOMP-MASH-QA.Q2_K.gguf +3 -0
KCOMP-MASH-QA.Q3_K_L.gguf +3 -0
KCOMP-MASH-QA.Q3_K_M.gguf +3 -0
KCOMP-MASH-QA.Q3_K_S.gguf +3 -0
KCOMP-MASH-QA.Q4_K_M.gguf +3 -0
KCOMP-MASH-QA.Q4_K_S.gguf +3 -0
KCOMP-MASH-QA.Q5_K_M.gguf +3 -0
KCOMP-MASH-QA.Q5_K_S.gguf +3 -0
KCOMP-MASH-QA.Q6_K.gguf +3 -0
KCOMP-MASH-QA.Q8_0.gguf +3 -0
KCOMP-MASH-QA.f16.gguf +3 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,15 @@ 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
+KCOMP-MASH-QA.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+KCOMP-MASH-QA.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+KCOMP-MASH-QA.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+KCOMP-MASH-QA.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+KCOMP-MASH-QA.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+KCOMP-MASH-QA.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+KCOMP-MASH-QA.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+KCOMP-MASH-QA.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+KCOMP-MASH-QA.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+KCOMP-MASH-QA.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+KCOMP-MASH-QA.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+KCOMP-MASH-QA.f16.gguf filter=lfs diff=lfs merge=lfs -text

KCOMP-MASH-QA.IQ4_XS.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:7055bbc7c34af0d627a56f3d093ab6c84d8a99010a2fccb2c7ab84ff15269a25
+size 1501221920

KCOMP-MASH-QA.Q2_K.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a47730cba604d748a820ff6a46f63b587360b12e7090f72d4ecc275e2f12d0d7
+size 1157927968

KCOMP-MASH-QA.Q3_K_L.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:b7ccc909c1d57b1b63aec7d693c24386ee27162bd418cc64e8eb0ec1e181b3ab
+size 1465594912

KCOMP-MASH-QA.Q3_K_M.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:cceffe08d5c86e4e3e75d10cfdc0e63b26a44f737a706614ff1879aa4b0d589f
+size 1383805984

KCOMP-MASH-QA.Q3_K_S.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:94da35378c5234e66779f8b26a8fd15de783b8a4fec6bc2160bf0ccf863206db
+size 1287984160

KCOMP-MASH-QA.Q4_K_M.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:905d4fb3de021c86cd59d12dbe47bba375b8aa5135804fd6594b1a6ab403bd39
+size 1630266400

KCOMP-MASH-QA.Q4_K_S.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5b8e7275de0b115de04bae9c793b060d3b655d335c2755b3953b5338e96d1b84
+size 1559843872

KCOMP-MASH-QA.Q5_K_M.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:7ecd04456fbb4b70c27f3c9c7c62c9707d970e45a737896bfe4e16cbfe12178d
+size 1839653920

KCOMP-MASH-QA.Q5_K_S.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:77d352aef9d6c341ca95af63f44e49b18d797a25c81f4e902569928ec7de2c33
+size 1798919200

KCOMP-MASH-QA.Q6_K.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:563276c5887bf648e449dee3106675d2c8290d86dbde3e45205d7c2be58b38e9
+size 2062128160

KCOMP-MASH-QA.Q8_0.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:4e758956f9dd88ad3288ef5284240071d0ee3561dcdcc3f5f2154d9b00f4205b
+size 2669074432

KCOMP-MASH-QA.f16.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:70f0ea65ec57a704ae16d3bdd215a0216229e6084090cbf41d988c424608f010
+size 5018543872