Instructions to use liodon-ai/ReaderLM-v2-imatrix-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 liodon-ai/ReaderLM-v2-imatrix-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 liodon-ai/ReaderLM-v2-imatrix-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf liodon-ai/ReaderLM-v2-imatrix-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 liodon-ai/ReaderLM-v2-imatrix-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf liodon-ai/ReaderLM-v2-imatrix-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 liodon-ai/ReaderLM-v2-imatrix-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf liodon-ai/ReaderLM-v2-imatrix-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 liodon-ai/ReaderLM-v2-imatrix-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf liodon-ai/ReaderLM-v2-imatrix-GGUF:Q4_K_M

Use Docker

docker model run hf.co/liodon-ai/ReaderLM-v2-imatrix-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use liodon-ai/ReaderLM-v2-imatrix-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "liodon-ai/ReaderLM-v2-imatrix-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": "liodon-ai/ReaderLM-v2-imatrix-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/liodon-ai/ReaderLM-v2-imatrix-GGUF:Q4_K_M

Ollama
How to use liodon-ai/ReaderLM-v2-imatrix-GGUF with Ollama:
```
ollama run hf.co/liodon-ai/ReaderLM-v2-imatrix-GGUF:Q4_K_M
```

Unsloth Studio

How to use liodon-ai/ReaderLM-v2-imatrix-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 liodon-ai/ReaderLM-v2-imatrix-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 liodon-ai/ReaderLM-v2-imatrix-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for liodon-ai/ReaderLM-v2-imatrix-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use liodon-ai/ReaderLM-v2-imatrix-GGUF with Docker Model Runner:
```
docker model run hf.co/liodon-ai/ReaderLM-v2-imatrix-GGUF:Q4_K_M
```

Lemonade

How to use liodon-ai/ReaderLM-v2-imatrix-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull liodon-ai/ReaderLM-v2-imatrix-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.ReaderLM-v2-imatrix-GGUF-Q4_K_M

List all available models

lemonade list

PY-AI-Dev commited on 14 days ago

Commit

e51bd74

verified ·

1 Parent(s): c676e96

Add iMatrix GGUF quantizations for ReaderLM-v2

Browse files

Files changed (9) hide show

.gitattributes +7 -0
README.md +64 -0
ReaderLM-v2-IQ2_M.gguf +3 -0
ReaderLM-v2-IQ3_M.gguf +3 -0
ReaderLM-v2-IQ4_XS.gguf +3 -0
ReaderLM-v2-Q4_K_M.gguf +3 -0
ReaderLM-v2-Q5_K_M.gguf +3 -0
ReaderLM-v2-Q6_K.gguf +3 -0
ReaderLM-v2-Q8_0.gguf +3 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,10 @@ 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
+ReaderLM-v2-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
+ReaderLM-v2-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+ReaderLM-v2-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+ReaderLM-v2-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+ReaderLM-v2-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+ReaderLM-v2-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+ReaderLM-v2-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md ADDED Viewed

	@@ -0,0 +1,64 @@

+---
+license: other
+base_model: jinaai/ReaderLM-v2
+pipeline_tag: text-generation
+tags:
+- gguf
+- local-llm
+- llama.cpp
+- lm-studio
+- quantized
+- imatrix
+- sub-4-bit
+- qwen2
+---
+# ReaderLM-v2 — iMatrix GGUF
+GGUF quantizations of [jinaai/ReaderLM-v2](https://huggingface.co/jinaai/ReaderLM-v2), published by [Liodon AI](https://huggingface.co/liodon-ai).
+## Quick Start
+**llama.cpp**
+```bash
+llama-cli -hf liodon-ai/ReaderLM-v2-imatrix-GGUF:Q4_K_M
+```
+**Ollama**
+```bash
+ollama run hf.co/liodon-ai/ReaderLM-v2-imatrix-GGUF:Q4_K_M
+```
+**LM Studio / Jan** — search `liodon-ai/ReaderLM-v2-imatrix-GGUF` and pick your quant.
+## Quants
+| Quant | Size | VRAM est. | Notes |
+|-------|------|-----------|-------|
+| `IQ2_M` | 0.60 GB | ~1 GB | 2-bit, iMatrix — smallest usable |
+| `IQ3_M` | 0.78 GB | ~1 GB | 3-bit, iMatrix — great quality/size tradeoff |
+| `IQ4_XS` | 0.90 GB | ~1 GB | 4-bit extra-small, iMatrix |
+| `Q4_K_M` | 0.99 GB | ~1 GB | 4-bit, iMatrix-calibrated (recommended) |
+| `Q5_K_M` | 1.13 GB | ~1 GB | 5-bit, iMatrix-calibrated |
+| `Q6_K` | 1.27 GB | ~1 GB | 6-bit, iMatrix-calibrated, near-lossless |
+| `Q8_0` | 1.65 GB | ~2 GB | 8-bit, essentially lossless |
+## What is iMatrix?
+Standard quantization treats all weights equally. iMatrix runs 128 calibration chunks through
+the full-precision model to find which weights matter most, then allocates more precision where
+it counts. At Q2/Q3/Q4 this means noticeably better coherence and instruction-following —
+**same file size, better output**.
+Calibration: 2M tokens of [WikiText-103](https://huggingface.co/datasets/wikitext).
+> Also see plain (non-iMatrix) quants: `liodon-ai/ReaderLM-v2-GGUF`
+## Source
+- **Model**: [jinaai/ReaderLM-v2](https://huggingface.co/jinaai/ReaderLM-v2)
+- **License**: other
+---
+*Quantized by [Liodon AI](https://huggingface.co/liodon-ai)*

ReaderLM-v2-IQ2_M.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:1cf015e755f242f7760a4d8e61ea10d58287166cbf4619d61c30364efe419f9d
+size 601052672

ReaderLM-v2-IQ3_M.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:1a053ee6ac4efd54107bbeb856f2c7d7c39480af07e596621719b8dc0c6ef708
+size 776662016

ReaderLM-v2-IQ4_XS.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:9f8c463ec3140ddcece7dde98a7f921357af1f2a45c894bc4e9e921d093417e3
+size 895729664

ReaderLM-v2-Q4_K_M.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:17c38fae674695071789b73690f266a15050489e5e2f47a43e018f9f8c338fb4
+size 986046464

ReaderLM-v2-Q5_K_M.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:54312172f4110df0296b243d209cd6156cf65ce5d68b39f3dbb2bbb49edd1edb
+size 1125048320

ReaderLM-v2-Q6_K.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:8bbfbc7720aaa92f8c3a67dffb4ae0fb4f2158e7c53f6cb60a5c25b5c13c31ee
+size 1272737792

ReaderLM-v2-Q8_0.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:36c448d5d167bfd6bac1d063093e92457ccee17258206490f8d79c56637ff38f
+size 1646571008