Sponsored by
Vmake Labs Video Enhancer
tencent / Youtu-LLM-2B-GGUF
Model's Last Updated: January 06 2026
text-generation
Introduction of Youtu-LLM-2B-GGUF
Model Details of Youtu-LLM-2B-GGUF
🎯 Brief Introduction
Youtu-LLM is a new, small, yet powerful LLM, contains only 1.96B parameters, supports 128k long context, and has native agentic talents. On general evaluations, Youtu-LLM significantly outperforms SOTA LLMs of similar size in terms of Commonsense, STEM, Coding and Long Context capabilities; in agent-related testing, Youtu-LLM surpasses larger-sized leaders and is truly capable of completing multiple end2end agent tasks.
Youtu-LLM has the following features:
- Type: Autoregressive Causal Language Models with Dense MLA
- Release versions: Base and Instruct
- Number of Parameters: 1.96B
- Number of Layers: 32
- Number of Attention Heads (MLA): 16 for Q/K/V
- MLA Rank: 1,536 for Q, 512 for K/V
- MLA Dim: 128 for QK Nope, 64 for QK Rope, and 128 for V
- Context Length: 131,072
- Vocabulary Size: 128,256
🤗 Model Download
| Model Name | Description | Download |
|---|---|---|
| Youtu-LLM-2B-Base | Base model of Youtu-LLM-2B | 🤗 Model |
| Youtu-LLM-2B | Instruct model of Youtu-LLM-2B | 🤗 Model |
| Youtu-LLM-2B-GGUF | Instruct model of Youtu-LLM-2B, in GGUF format | 🤗 Model |
📊 Performance Comparisons
Instruct Model
General Benchmarks
| Benchmark | DeepSeek-R1-Distill-Qwen-1.5B | Qwen3-1.7B | SmolLM3-3B | Qwen3-4B | DeepSeek-R1-Distill-Llama-8B | Youtu-LLM-2B |
|---|---|---|---|---|---|---|
| Commonsense Knowledge Reasoning | ||||||
| MMLU-Redux | 53.0% | 74.1% | 75.6% | 83.8% | 78.1% | 75.8% |
| MMLU-Pro | 36.5% | 54.9% | 53.0% | 69.1% | 57.5% | 61.6% |
| Instruction Following & Text Reasoning | ||||||
| IFEval | 29.4% | 70.4% | 60.4% | 83.6% | 34.6% | 81.2% |
| DROP | 41.3% | 72.5% | 72.0% | 82.9% | 73.1% | 86.7% |
| MUSR | 43.8% | 56.6% | 54.1% | 60.5% | 59.7% | 57.4% |
| STEM | ||||||
| MATH-500 | 84.8% | 89.8% | 91.8% | 95.0% | 90.8% | 93.7% |
| AIME 24 | 30.2% | 44.2% | 46.7% | 73.3% | 52.5% | 65.4% |
| AIME 25 | 23.1% | 37.1% | 34.2% | 64.2% | 34.4% | 49.8% |
| GPQA-Diamond | 33.6% | 36.9% | 43.8% | 55.2% | 45.5% | 48.0% |
| BBH | 31.0% | 69.1% | 76.3% | 87.8% | 77.8% | 77.5% |
| Coding | ||||||
| HumanEval | 64.0% | 84.8% | 79.9% | 95.4% | 88.1% | 95.9% |
| HumanEval+ | 59.5% | 76.2% | 74.7% | 87.8% | 82.5% | 89.0% |
| MBPP | 51.5% | 80.5% | 66.7% | 92.3% | 73.9% | 85.0% |
| MBPP+ | 44.2% | 67.7% | 56.7% | 77.6% | 61.0% | 71.7% |
| LiveCodeBench v6 | 19.8% | 30.7% | 30.8% | 48.5% | 36.8% | 43.7% |
Agentic Benchmarks
| Benchmark | Qwen3-1.7B | SmolLM3-3B | Qwen3-4B | Youtu-LLM-2B |
|---|---|---|---|---|
| Deep Research | ||||
| GAIA | 11.4% | 11.7% | 25.5% | 33.9% |
| xbench | 11.7% | 13.9% | 18.4% | 19.5% |
| Code | ||||
| SWE-Bench-Verified | 0.6% | 7.2% | 5.7% | 17.7% |
| EnConda-Bench | 10.8% | 3.5% | 16.1% | 21.5% |
| Tool | ||||
| BFCL V3 | 55.5% | 31.5% | 61.7% | 58.0% |
| τ²-Bench | 2.6% | 9.7% | 10.9% | 15.0% |
🚀 Quick Start
This guide will help you quickly deploy and invoke the Youtu-LLM-2B model. This model supports "Reasoning Mode", enabling it to generate higher-quality responses through Chain of Thought (CoT).
Server Example
Enable Reasoning Mode (default):
./llama-server -m Youtu-LLM-2B-F16.gguf \
--port 8080 \
--host 0.0.0.0
Disable Reasoning Mode:
./llama-server -m Youtu-LLM-2B-F16.gguf \
--port 8080 \
--host 0.0.0.0 \
--reasoning-budget 0
Key Configuration Details
Reasoning Mode Toggle
Controlled via the
--reasoning-budget
parameter:
-
Default (no flag):
Enables Chain of Thought; ideal for complex logic and reasoning tasks. Response includes
reasoning_contentfield. -
--reasoning-budget 0: Disables reasoning; faster response time, suitable for simple conversations.
Recommended Decoding Parameters
| Parameter | Reasoning Mode | Normal Mode |
|---|---|---|
temperature
|
1.0 (Maintains creativity) | 0.7 (More stable results) |
top_p
|
0.95 | 0.8 |
top_k
|
20 | 20 |
repetition_penalty
|
1.05 | - |
Tip: When using Reasoning Mode, a higher
temperaturehelps the model perform deeper, more divergent thinking.
📚 Citation
If you find our work useful in your research, please consider citing the following paper:
@article{youtu-llm,
title={Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models},
author={Tencent Youtu Lab},
year={2025},
eprint={2512.24618},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2512.24618},
}
Runs of tencent Youtu-LLM-2B-GGUF on huggingface.co
1.0K
Total runs
0
24-hour runs
33
3-day runs
33
7-day runs
33
30-day runs
More Information About Youtu-LLM-2B-GGUF huggingface.co Model
Url of Youtu-LLM-2B-GGUF
Youtu-LLM-2B-GGUF huggingface.co Url
Provider of Youtu-LLM-2B-GGUF huggingface.co
Other API from tencent
Total runs:
744.8K
Run Growth:
606.4K
Growth Rate:
93.98%
Total runs:
295.8K
Run Growth:
-65.8K
Growth Rate:
-22.35%
Total runs:
137.5K
Run Growth:
33.1K
Growth Rate:
25.09%
Total runs:
90.7K
Run Growth:
-582.4K
Growth Rate:
-642.43%
Total runs:
71.3K
Run Growth:
25.9K
Growth Rate:
35.52%
Total runs:
69.3K
Run Growth:
9.9K
Growth Rate:
15.24%
Total runs:
43.4K
Run Growth:
10.6K
Growth Rate:
26.09%
Total runs:
33.2K
Run Growth:
15.6K
Growth Rate:
54.83%
Total runs:
26.1K
Run Growth:
3.6K
Growth Rate:
16.73%
Total runs:
21.1K
Run Growth:
9.3K
Growth Rate:
47.64%
Total runs:
19.5K
Run Growth:
4.0K
Growth Rate:
22.38%
Total runs:
15.9K
Run Growth:
-3.1K
Growth Rate:
-19.78%
Total runs:
15.1K
Run Growth:
5.1K
Growth Rate:
35.51%
Total runs:
14.7K
Run Growth:
-29.1K
Growth Rate:
-141.02%
Total runs:
14.5K
Run Growth:
-5.1K
Growth Rate:
-34.94%
Total runs:
6.1K
Run Growth:
6.1K
Growth Rate:
100.00%
Total runs:
5.6K
Run Growth:
1
Growth Rate:
0.02%
Total runs:
4.9K
Run Growth:
2.1K
Growth Rate:
42.89%
Total runs:
4.9K
Run Growth:
-606
Growth Rate:
-13.10%
Total runs:
3.8K
Run Growth:
3.2K
Growth Rate:
85.37%
Total runs:
3.4K
Run Growth:
24
Growth Rate:
0.75%
Total runs:
3.1K
Run Growth:
-109
Growth Rate:
-3.57%
Total runs:
2.9K
Run Growth:
-19.0K
Growth Rate:
-490.95%
Total runs:
2.5K
Run Growth:
-32.3K
Growth Rate:
-219.03%
Total runs:
2.0K
Run Growth:
-1.9K
Growth Rate:
-85.29%
Total runs:
1.8K
Run Growth:
327
Growth Rate:
17.71%
Total runs:
1.8K
Run Growth:
1.2K
Growth Rate:
71.60%
Total runs:
1.7K
Run Growth:
-1.0K
Growth Rate:
-51.94%
Total runs:
1.7K
Run Growth:
-873
Growth Rate:
-51.17%
Total runs:
1.6K
Run Growth:
-112
Growth Rate:
-7.50%
Total runs:
1.6K
Run Growth:
156
Growth Rate:
5.51%
Total runs:
1.5K
Run Growth:
-129
Growth Rate:
-8.84%
Total runs:
1.4K
Run Growth:
1.2K
Growth Rate:
82.02%
Total runs:
1.4K
Run Growth:
954
Growth Rate:
70.10%
Total runs:
1.3K
Run Growth:
-281
Growth Rate:
-8.99%
Total runs:
1.3K
Run Growth:
-288
Growth Rate:
-21.74%
Total runs:
1.2K
Run Growth:
-38.3K
Growth Rate:
-2589.19%
Total runs:
945
Run Growth:
487
Growth Rate:
52.25%
Total runs:
915
Run Growth:
-1.8K
Growth Rate:
-195.08%
Total runs:
824
Run Growth:
188
Growth Rate:
22.82%
Total runs:
719
Run Growth:
243
Growth Rate:
37.67%
Total runs:
693
Run Growth:
-114
Growth Rate:
-16.45%
Total runs:
686
Run Growth:
529
Growth Rate:
57.63%
Total runs:
662
Run Growth:
243
Growth Rate:
36.27%
Total runs:
643
Run Growth:
301
Growth Rate:
47.18%
Total runs:
630
Run Growth:
450
Growth Rate:
66.86%
Total runs:
598
Run Growth:
-328
Growth Rate:
-49.40%
Total runs:
584
Run Growth:
201
Growth Rate:
34.48%
Total runs:
546
Run Growth:
-1.6K
Growth Rate:
-291.22%
Total runs:
520
Run Growth:
-262
Growth Rate:
-53.80%
Total runs:
480
Run Growth:
79
Growth Rate:
16.46%
Total runs:
476
Run Growth:
318
Growth Rate:
57.61%
Total runs:
463
Run Growth:
-25
Growth Rate:
-5.40%
Total runs:
394
Run Growth:
147
Growth Rate:
35.68%
Total runs:
387
Run Growth:
169
Growth Rate:
45.92%
Total runs:
369
Run Growth:
180
Growth Rate:
45.34%
Total runs:
320
Run Growth:
171
Growth Rate:
51.35%
Total runs:
297
Run Growth:
-416
Growth Rate:
-140.07%
Total runs:
295
Run Growth:
221
Growth Rate:
44.65%
Total runs:
290
Run Growth:
-86
Growth Rate:
-29.66%
Total runs:
282
Run Growth:
71
Growth Rate:
24.40%
Total runs:
280
Run Growth:
-137
Growth Rate:
-48.93%
Total runs:
277
Run Growth:
-69
Growth Rate:
-24.91%
Total runs:
266
Run Growth:
86
Growth Rate:
31.97%
Total runs:
247
Run Growth:
72
Growth Rate:
29.75%
Total runs:
238
Run Growth:
98
Growth Rate:
43.17%
Total runs:
233
Run Growth:
64
Growth Rate:
24.33%
Total runs:
229
Run Growth:
44
Growth Rate:
19.21%
Total runs:
227
Run Growth:
104
Growth Rate:
43.88%
Total runs:
212
Run Growth:
9
Growth Rate:
4.25%