Downloads · 30 days
22
51% of all-time downloads
xLAM-1b-fc-r-RKLLM-v1.2.3
GatekeeperZA/xLAM-1b-fc-r-RKLLM-v1.2.3
xLAM-1b-fc-r-RKLLM-v1.2.3 is a text generation model from GatekeeperZA. Use it when you need the model to write or continue text. It is set up for rkllm. The card lists the license as cc-by-nc-4.0.
Pre-converted Salesforce/xLAM-1b-fc-r for the Rockchip RK3588 NPU using rknn-llm runtime v1.2.3.
All-time downloads
43
Public
Repo size
1.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.rkllm1.4 GB · 100%
At a glance
- Task
- Text Generation
- Library
- rkllm
- License
- cc-by-nc-4.0
- Access
- Public
- Created
- Aug 15, 2026
- Updated
- Aug 15, 2026
- SHA
- f4e4b763
Try a prompt
Base models
Model card
From the Hugging Face model README
xLAM-1b-fc-r for RKLLM v1.2.3 (RK3588 NPU)
Pre-converted Salesforce/xLAM-1b-fc-r for the Rockchip RK3588 NPU using rknn-llm runtime v1.2.3.
Runs on Orange Pi 5 Plus, Rock 5B, Radxa NX5, and other RK3588-based SBCs with 8GB+ RAM.
xLAM-1b-fc-r achieves 78.94% on BFCL v3 — the highest function-calling accuracy of any model under 2B parameters. Based on DeepSeek-Coder-1.3B with Salesforce's xLAM function-calling fine-tune.
Files
| File | Size | Description |
|---|---|---|
xLAM-1b-fc-r-rk3588-v123-w8a8.rkllm | 1.4 GB | LLM (W8A8 quantized, 8192 token context) |
Why xLAM-1b-fc-r?
This model is the best option for on-device tool calling on RK3588 hardware:
| Model | Params | BFCL v3 Accuracy | Notes |
|---|---|---|---|
| xLAM-1b-fc-r | 1.1B | 78.94% | Best sub-2B for function calling |
| Qwen2.5-1.5B-Instruct | 1.5B | ~40-50% | General instruct, not FC-tuned |
| Llama-3.2-1B | 1.2B | ~30-40% | General purpose |
For general chat and reasoning, pair it with GatekeeperZA/Qwen2.5-1.5B-Instruct-RKLLM-v1.2.3.
Quick Start
Directory Structure
~/models/xLAM-1b-fc-r/
xLAM-1b-fc-r-rk3588-v123-w8a8.rkllm
Using with RKLLM API Server
This model is designed for use with the RKLLM API Server, which provides an OpenAI-compatible API for RK3588 NPU inference.
mkdir -p ~/models/xLAM-1b-fc-r
# Copy .rkllm file here — the API server will find it automatically
sudo systemctl restart rkllm-api
The model will appear as xlam-1b-fc-r in the OpenAI-compatible model list.
Function Calling Format
xLAM uses a specific prompt format for tool calling. Refer to the original model card for the system prompt template and JSON tool schema format.
Export Details
| Parameter | Value |
|---|---|
| Source | Salesforce/xLAM-1b-fc-r |
| Base architecture | DeepSeek-Coder-1.3B |
| Tool | rkllm-toolkit v1.2.3 |
| Quantization | W8A8 (8-bit weights, 8-bit activations) |
| Optimization level | 1 |
| Target platform | rk3588 |
| NPU cores | 3 |
| Max context | 8192 tokens |
Performance Benchmarks
Tested on Orange Pi 5 Plus (16GB RAM), RK3588 SoC, RKNPU driver 0.9.8:
| Metric | Value |
|---|---|
| Decode speed | ~20 tok/s (estimated) |
| Model load time | ~2 s |
| Peak RAM | ~1.6 GB |
Known Limitations
- General reasoning: xLAM-1b-fc-r is fine-tuned for function calling, not general chat. Use Qwen2.5-1.5B for open-ended tasks.
- Context: Compiled at 8192 tokens. The runtime will truncate inputs that exceed this limit.
- Version lock: This file requires RKLLM runtime v1.2.3 and NPU driver v0.9.8. It is not compatible with v1.3.0 or later runtimes.
- License: The original xLAM-1b-fc-r is CC-BY-NC-4.0 (non-commercial). This converted file inherits that license.
License
CC-BY-NC-4.0, inherited from Salesforce/xLAM-1b-fc-r. Non-commercial use only.
Credits
- Model: Salesforce AI Research for xLAM-1b-fc-r
- Runtime: Rockchip / airockchip for rkllm-toolkit
- API Server: RKLLM API Server — OpenAI-compatible server for RK3588 NPU
- Task
- Text Generation
- Library
- rkllm
- License
- cc-by-nc-4.0
- Created
- Aug 15, 2026
- Updated
- Aug 15, 2026