---
base_model: LiquidAI/LFM2.5-Embedding-350M
language:
  - en
  - de
  - fr
  - es
  - it
  - pt
  - nl
  - pl
  - ru
  - ja
  - zh
license: other
license_name: lfm1.0
license_link: https://huggingface.co/LiquidAI/LFM2.5-Embedding-350M/blob/main/LICENSE
tags:
  - gguf
  - embedding
  - retrieval
  - text-embeddings-inference
  - crispembed
---

# LFM2.5-Embedding-350M — CrispEmbed GGUF

CrispEmbed-native GGUF quantizations of [LiquidAI/LFM2.5-Embedding-350M](https://huggingface.co/LiquidAI/LFM2.5-Embedding-350M).

**Format note:** These GGUFs use CrispEmbed's internal tensor naming (`lfm.*` prefix, arch=`lfm2`). They are **not** interchangeable with the [official LiquidAI GGUFs](https://huggingface.co/LiquidAI/LFM2.5-Embedding-350M-GGUF) which target llama.cpp (`lfm2-bidir` arch, `blk.*` tensor naming). Use the LiquidAI GGUFs if you want llama.cpp/llama-server.

---

## Files

| File | Size | Description |
|------|------|-------------|
| `lfm2-embed-q8_0.gguf` | 359 MB | 8-bit quantization — best accuracy, recommended |
| `lfm2-embed-q4_k.gguf` | 222 MB | 4-bit K-quant — 3× compression, minimal quality loss |
| `lfm2-embed-f16.gguf` | 678 MB | Full fp16 — reference precision |

## Parity (CrispEmbed q8_0 vs HF float32 `Lfm2BidirectionalModel`)

| Stage | Cosine | Notes |
|-------|--------|-------|
| per-layer (all 20) | ≥ 0.9999 | measured on 3-token input via test-lfm2-diff |
| CLS embedding q8_0 | **0.9999** | 5 diverse test sentences |
| CLS embedding q4_k | **0.982** | expected q4_k quantization floor |

## Model

- **Architecture**: 16-layer hybrid (10 ShortConv + 6 GQA attention), hidden=1024
- **Pooling**: CLS token (position 0) of last hidden state, L2-normalized
- **Dimension**: 1024
- **Languages**: 11 (en, de, fr, es, it, pt, nl, pl, ru, ja, zh)
- **Parameters**: 350M
- **Task prefixes**: `"query: "` for queries, `"document: "` for passages

## Usage with CrispEmbed

### CLI

```bash
# Download
./crispembed --download lfm2-embed

# Embed a query (prefix auto-applied)
./crispembed -m ~/.cache/crispembed/lfm2-embed-q8_0.gguf "What is the capital of France?"

# Embed a document (disable auto-prefix and supply explicitly, or use --prefix)
./crispembed -m ~/.cache/crispembed/lfm2-embed-q8_0.gguf \
  --prefix "document: " "Paris is the capital of France."

# JSON output for downstream use
./crispembed -m ~/.cache/crispembed/lfm2-embed-q8_0.gguf --json "query: machine learning"
```

### Python (via [crispembed Python bindings](https://github.com/CrispStrobe/CrispEmbed))

```python
import crispembed

model = crispembed.load("~/.cache/crispembed/lfm2-embed-q8_0.gguf")

query_emb = model.encode("query: What is the capital of France?")
doc_emb   = model.encode("document: Paris is the capital of France.")

import numpy as np
score = np.dot(query_emb, doc_emb)  # both are already L2-normalized
print(f"Similarity: {score:.4f}")
```

### Rust

```rust
use crispembed::CrispEmbed;

let model = CrispEmbed::load("lfm2-embed-q8_0.gguf")?;
let emb = model.encode("query: hello world")?;
```

## Comparison with official LiquidAI GGUFs

| | This repo | [LiquidAI/LFM2.5-Embedding-350M-GGUF](https://huggingface.co/LiquidAI/LFM2.5-Embedding-350M-GGUF) |
|---|---|---|
| Runtime | [CrispEmbed](https://github.com/CrispStrobe/CrispEmbed) | llama.cpp / llama-server |
| GGUF arch tag | `lfm2` | `lfm2-bidir` |
| Tensor naming | `lfm.*` prefix | `blk.*` / llama.cpp convention |
| Quantizations | f16, q8_0, q4_k | BF16, F16, Q4_0, Q4_K_M, Q5_K_M, Q6_K, Q8_0 |
| q8_0 size | 359 MB | 379 MB |
| Metal GPU | Yes (Apple Silicon) | Yes |

## Conversion

Convert from the source model yourself:

```bash
git clone https://github.com/CrispStrobe/CrispEmbed
cd CrispEmbed

# Download source
python models/convert-lfm2-embed-to-gguf.py \
    --model LiquidAI/LFM2.5-Embedding-350M \
    --output lfm2-embed-f16.gguf --dtype f16

# Quantize
./build/crispembed-quantize lfm2-embed-f16.gguf lfm2-embed-q8_0.gguf q8_0
./build/crispembed-quantize lfm2-embed-f16.gguf lfm2-embed-q4_k.gguf q4_k
```

## License

[LFM1.0](https://huggingface.co/LiquidAI/LFM2.5-Embedding-350M/blob/main/LICENSE) — same as the base model.