Instructions to use KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-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 KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-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 KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-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 KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-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 KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-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 KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-GGUF:Q4_K_M

Use Docker

docker model run hf.co/KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-GGUF with Ollama:
```
ollama run hf.co/KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-GGUF:Q4_K_M
```

Unsloth Studio

How to use KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-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 KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-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 KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-GGUF with Docker Model Runner:
```
docker model run hf.co/KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-GGUF:Q4_K_M
```

Lemonade

How to use KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.KaLM-Reranker-V1-Small-Q4_K_M-GGUF-Q4_K_M

List all available models

lemonade list

KaLM-Reranker-V1-Small-Q4_K_M-GGUF / EVALUATION.md

cosyy

Remove internal evaluation terminology from public release metadata

ee5f1d9 verified 24 days ago

preview code

Raw

History Blame Contribute Delete

1.08 kB

Complete FIQA Q4_K_M evaluation

Model: KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-GGUF

Scope and ranking contract

BEIR FiQA complete test set: 648 queries.
Frozen retriever top-100: 64,800 query/passage pairs.
Rank by margin descending, then retriever rank and passage ID.
Encoder/query limits: 1,024/512 tokens; encoder chunk size: 4.

Metrics

Model	NDCG@10	MAP@10	Recall@10	MRR@10	NDCG@100
Retriever	0.46985	0.38419	0.55188	0.54942	0.53769
Transformers/BF16	0.55255	0.46851	0.62310	0.63469	0.60417
GGUF Q4_K_M	0.55208	0.46747	0.62503	0.63452	0.60340

The Q4_K_M gate allows a maximum 0.020 BF16 drop for both NDCG@10 and MRR@10. Observed drops are 0.00047 and 0.00017. Gate status: accepted.

Recorded throughput: 26.634 pairs/s across 81 completed shards. This number is hardware- and scheduling-specific.

Provenance

The release manifest records SHA256 values for the source evaluation manifest, metrics, efficiency, validation and summary.