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/Qwen2.5-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Benchmark: sakthai-bench-v2 · 500 samples · run 2026-08-01
Overall (strict): 38.78 · Selection: 38.78 · Arguments: 45.53
| Category | Count | Selection | Arguments | Strict |
|---|---|---|---|---|
| irrelevance_no_tools | 50 | 100.00 | 100.00 | 100.00 |
| irrelevance_tools | 150 | 79.33 | 100.00 | 79.33 |
| parallel | 137 | 0.00 | 0.00 | 0.00 |
| simple | 122 | 7.38 | 7.38 | 7.38 |
| held_out | - | 10.71 | 10.71 | 10.71 |
SakThai Context 7B Merged is a merged/continued checkpoint from the SakThai context family. It combines tool-use behaviour from Nanthasit/sakthai-context-7b-tools with long-context capability from Nanthasit/sakthai-context-7b-128k, continuing from Qwen/Qwen2.5-7B-Instruct.
It is intended for:
<tools> XML prompt formattingpython
from transformers import AutoTokenizer, AutoModelForCausalLMmodel_id = "Nanthasit/sakthai-context-7b-merged"tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")messages = [{"role": "user", "content": "List your available tools first, then find today's weather in Bangkok."}]prompt = tokenizer.apply_chat_template(messages, tokenize=False)inputs = tokenizer(prompt, return_tensors="pt").to(model.device)out = model.generate(**inputs, max_new_tokens=512)print(tokenizer.decode(out[0], skip_special_tokens=True))
For GGUF inference:
python
from llama_cpp import Llamallm = Llama(model_path="sakthai-context-7b-merged.Q4_K_M.gguf", n_ctx=32768, n_threads=8)out = llm("<|user|>\nWhat tools do you have?\n<|assistant|>\n", max_tokens=256)print(out["choices"][0]["text"])
This line was trained/evaluated against SakThai tool-use corpora:
Nanthasit/sakthai-combined-v6Nanthasit/sakthai-combined-v7Nanthasit/sakthai-combined-v8Nanthasit/sakthai-context-7b-toolsNanthasit/sakthai-context-7b-128kEvaluation artifacts are preserved under .eval_results/ in this repository.
Baseline comparisons should reference sibling cards:
Nanthasit/sakthai-context-7b-toolsNanthasit/sakthai-context-7b-128k<tools> XML blocks.This checkpoint continues from prior SakThai context model merges. Datasets used earlier in the lineage include:
Nanthasit/sakthai-combined-v6Nanthasit/sakthai-combined-v7Nanthasit/sakthai-combined-v8See eval/ and .eval_results/ in this repo for local evaluation artifacts.
bibtex
@misc{sakthai-context-7b-merged,title = {SakThai Context 7B Merged},author = {Nanthasit (Beer)},year = {2026},url = {https://huggingface.co/Nanthasit/sakthai-context-7b-merged}}
MIT