GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
Nanthasit
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
Nanthasit
Model Tree
Qwen/Qwen2.5-1.5B-Instruct
Input Modalities
Output Modalities
Supported Functionality
LoRA weights (r=16, alpha=32) for Qwen2.5-1.5B-Instruct, trained on sakthai-combined-v6 + sakthai-combined-v7 + irrelevance-supplement. For a single ready-to-run GGUF checkpoint, use the merged model: sakthai-context-1.5b-merged.
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModelbase = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct", torch_dtype=torch.float16, device_map="auto")tok = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct")model = PeftModel.from_pretrained(base, "Nanthasit/sakthai-context-1.5b-tools")# model.merge_and_unload() to bake the adapter in
For best tool-calling, pass tool schemas in a <tools> block and use temperature ≈ 0.01–0.1.
| Base model | Qwen/Qwen2.5-1.5B-Instruct |
| Method | QLoRA (4-bit) |
| LoRA config | r=16, alpha=32, targets q/k/v/o_proj |
| Data | combined-v6 (2,003) + combined-v7 (2,309) + irrelevance-supplement (60) |
| Format / context | ChatML with tool schema · 32K tokens |
| Model | Size | Role |
|---|---|---|
| context-1.5b-merged | 934 MB | Flagship tool-calling GGUF |
| context-0.5b-merged | 380 MB | Lightweight / edge |
| context-7b-merged | 15 GB | Full-power reasoning |
| context-7b-128k |
14 models in the family · 8 datasets · 3 Spaces — full collection →
House of Sak · GitHub · All models · Collection
Apache 2.0 (following the Qwen2.5 base model license).
Not independently benchmarked. Earlier versions of this card carried a
model-index score derived from a small internal spot check (typically 5 or 8
hand-picked examples) presented as a benchmark result. Those entries have been
removed rather than left to propagate through Hub metadata.
For tool-calling models in this family, the benchmark to use is sakthai-bench-v2 — 500 rows, balanced across simple / parallel / irrelevance, with held-out tools and multi-turn coverage. Results will be published here once this model has been run against it.
*"We are one family — and becoming more." 🏠
| 15 GB |
| 128K long-context |
| context-{7b,1.5b,0.5b}-tools | LoRA | Tool-calling adapters ⬅ |
| context-1.5b-tools-v2 🆕 | 934 MB | Improved tool-calling merged GGUF |
| coder-1.5b | 1.1 GB | Code generation |
| vision-7b | 3.9 GB | Image→text (LLaVA) |
| embedding-multilingual | 80 MB | Cross-lingual embeddings |
| tts-model | 141 MB | Text-to-speech, 15 langs |