Total runs:
1.4K
Run Growth:
-102
Growth Rate:
-7.28%
Sponsored by
iMean AI Trip Planner
AXERA-TECH / InternVL2_5-1B
Model's Last Updated: September 22 2025
image-text-to-text
Introduction of InternVL2_5-1B
Model Details of InternVL2_5-1B
InternVL2_5-1B-Int8
This version of InternVL2_5-1B has been converted to run on the Axera NPU using w8a16 quantization.
This model has been optimized with the following LoRA:
Compatible with Pulsar2 version: 3.3
Convert tools links:
For those who are interested in model conversion, you can try to export axmodel through the original repo : https://huggingface.co/OpenGVLab/InternVL2_5-1B
Pulsar2 Link, How to Convert LLM from Huggingface to axmodel
Support Platform
-
AX650
- AX650N DEMO Board
- M4N-Dock(爱芯派Pro)
- M.2 Accelerator card
-
AX630C
- developing
| Chips | image encoder 448 | ttft | w8a16 |
|---|---|---|---|
| AX650 | 350 ms | 420 ms | 32 tokens/sec |
How to use
Download all files from this repository to the device
root@ax650:/mnt/qtang/llm-test/temp/InternVL2_5-1B# tree -L 1
.
|-- config.json
|-- internvl2_5_1b_448_ax650
|-- internvl2_5_tokenizer
|-- internvl2_5_tokenizer_448.py
|-- main_internvl2_5_448_prefill
|-- run_internvl2_5_448_ax650.sh
`-- ssd_car.jpg
Install transformer
pip install transformers==4.41.1
Start the Tokenizer service
root@ax650:/mnt/qtang/llm-test/temp/InternVL2_5-1B# python3 internvl2_5_tokenizer_448.py --port 12345
None None 151645 <|im_end|>
[151644, 8948, 198, 56568, 104625, 100633, 104455, 104800, 101101, 32022, 102022, 99602, 100013, 9370, 90286, 21287,
42140, 53772, 35243, 26288, 104949, 3837, 105205, 109641, 67916, 30698, 11, 54851, 46944, 115404, 42192, 99441, 100623,
48692, 100168, 110498, 1773, 151645, 151644, 872, 198, 151665, 151667, 151667, 151667, 151667, 151667, 151667, 151667,
151667, 151667, 151667, 151667, 151667, 151667, 151667, 151667, 151667, 151667, 151667, 151667, 151667, 151667, 151667,
......
151667, 151667, 151667, 151667, 151667, 151667, 151667, 151667, 151667, 151667, 151667, 151667, 151667, 151667, 151667,
198, 5501, 7512, 279, 2168, 19620, 13, 151645, 151644, 77091, 198]
310
[151644, 8948, 198, 56568, 104625, 100633, 104455, 104800, 101101, 32022, 102022, 99602, 100013, 9370, 90286, 21287,
42140, 53772, 35243, 26288, 104949, 3837, 105205, 109641, 67916, 30698, 11, 54851, 46944, 115404, 42192, 99441, 100623,
48692, 100168, 110498, 1773, 151645, 151644, 872, 198, 14990, 1879, 151645, 151644, 77091, 198]
47
http://localhost:12345
Inference with AX650 Host, such as M4N-Dock(爱芯派Pro) or AX650N DEMO Board
- input text
Describe the picture
- input image
Open another terminal and run
./run_internvl2_5_448_ax650.sh
root@ax650:/mnt/qtang/llm-test/temp/InternVL2_5-1B# ./run_internvl2_5_448_ax650.sh
[I][ Init][ 127]: LLM init start
bos_id: -1, eos_id: 151645
3% | ██ | 1 / 28 [0.01s<0.14s, 200.00 count/s] tokenizer init ok
[I][ Init][ 26]: LLaMaEmbedSelector use mmap
100% | ████████████████████████████████ | 28 / 28 [1.42s<1.42s, 19.66 count/s] init vpm axmodel ok,remain_cmm(2859 MB)B)
[I][ Init][ 275]: max_token_len : 1023
[I][ Init][ 280]: kv_cache_size : 128, kv_cache_num: 1023
[I][ Init][ 288]: prefill_token_num : 320
[I][ Init][ 290]: vpm_height : 448,vpm_width : 448
[I][ Init][ 299]: LLM init ok
Type "q" to exit, Ctrl+c to stop current running
prompt >> Describe the picture
image >> ssd_car.jpg
[I][ Encode][ 358]: image encode time : 362.987000 ms, size : 229376
[I][ Run][ 569]: ttft: 426.75 ms
The image depicts a scene on a city street with a prominent red double-decker bus in the background.
The bus is adorned with an advertisement that reads, "THINGS GET MORE EXCITING WHEN YOU SAY YES."
The bus is traveling on a road with a white bicycle lane marked on it. The street is lined with buildings,
and there is a black car parked on the side of the road. A woman is standing in the foreground, smiling at the camera.
She is wearing a black jacket and a scarf. The overall atmosphere suggests a typical urban setting,
possibly in a city known for its iconic double-decker buses.
[N][ Run][ 708]: hit eos,avg 31.90 token/s
prompt >> q
root@ax650:/mnt/qtang/llm-test/temp/InternVL2_5-1B#
Inference with M.2 Accelerator card
What is M.2 Accelerator card? , Show this DEMO based on Raspberry PI 5.
TODO
Runs of AXERA-TECH InternVL2_5-1B on huggingface.co
23
Total runs
1
24-hour runs
0
3-day runs
-2
7-day runs
-2
30-day runs
More Information About InternVL2_5-1B huggingface.co Model
Url of InternVL2_5-1B
InternVL2_5-1B huggingface.co Url
Provider of InternVL2_5-1B huggingface.co
Other API from AXERA-TECH
Updated:August 26 2026
Total runs:
195
Run Growth:
64
Growth Rate:
32.82%
Total runs:
104
Run Growth:
-359
Growth Rate:
-345.19%
Total runs:
68
Run Growth:
60
Growth Rate:
88.24%
Total runs:
61
Run Growth:
21
Growth Rate:
34.43%
Total runs:
52
Run Growth:
52
Growth Rate:
100.00%
Total runs:
49
Run Growth:
26
Growth Rate:
53.06%
Total runs:
48
Run Growth:
21
Growth Rate:
43.75%
Total runs:
46
Run Growth:
17
Growth Rate:
36.96%
Total runs:
46
Run Growth:
-1
Growth Rate:
-2.17%
Total runs:
45
Run Growth:
29
Growth Rate:
64.44%
Total runs:
45
Run Growth:
13
Growth Rate:
28.89%
Total runs:
45
Run Growth:
-2
Growth Rate:
-4.44%
Total runs:
43
Run Growth:
-2
Growth Rate:
-4.65%
Total runs:
41
Run Growth:
-19
Growth Rate:
-46.34%
Total runs:
41
Run Growth:
30
Growth Rate:
73.17%
Total runs:
40
Run Growth:
7
Growth Rate:
17.50%
Total runs:
40
Run Growth:
-7
Growth Rate:
-17.50%
Total runs:
39
Run Growth:
2
Growth Rate:
5.13%
Total runs:
38
Run Growth:
-195
Growth Rate:
-513.16%
Total runs:
37
Run Growth:
20
Growth Rate:
54.05%
Total runs:
37
Run Growth:
0
Growth Rate:
0.00%
Total runs:
36
Run Growth:
-34
Growth Rate:
-94.44%
Total runs:
35
Run Growth:
6
Growth Rate:
17.14%
Total runs:
34
Run Growth:
26
Growth Rate:
76.47%
Total runs:
34
Run Growth:
14
Growth Rate:
41.18%
Total runs:
34
Run Growth:
22
Growth Rate:
64.71%
Total runs:
31
Run Growth:
-12
Growth Rate:
-38.71%
Total runs:
31
Run Growth:
19
Growth Rate:
61.29%
Total runs:
31
Run Growth:
11
Growth Rate:
35.48%
Total runs:
31
Run Growth:
-1
Growth Rate:
-3.23%
Total runs:
31
Run Growth:
-2
Growth Rate:
-6.45%
Total runs:
31
Run Growth:
5
Growth Rate:
16.13%
Total runs:
30
Run Growth:
14
Growth Rate:
46.67%
Total runs:
30
Run Growth:
30
Growth Rate:
100.00%
Total runs:
30
Run Growth:
29
Growth Rate:
100.00%
Total runs:
29
Run Growth:
17
Growth Rate:
58.62%
Total runs:
29
Run Growth:
3
Growth Rate:
10.34%
Total runs:
29
Run Growth:
7
Growth Rate:
24.14%
Total runs:
28
Run Growth:
4
Growth Rate:
14.29%
Total runs:
28
Run Growth:
19
Growth Rate:
67.86%
Total runs:
28
Run Growth:
5
Growth Rate:
17.86%
Total runs:
28
Run Growth:
13
Growth Rate:
46.43%
Total runs:
26
Run Growth:
6
Growth Rate:
23.08%
Total runs:
26
Run Growth:
11
Growth Rate:
42.31%
Total runs:
25
Run Growth:
0
Growth Rate:
0.00%
Total runs:
25
Run Growth:
17
Growth Rate:
68.00%
Total runs:
25
Run Growth:
18
Growth Rate:
72.00%
Total runs:
25
Run Growth:
16
Growth Rate:
64.00%
Total runs:
24
Run Growth:
1
Growth Rate:
4.17%
Total runs:
24
Run Growth:
10
Growth Rate:
41.67%
Total runs:
24
Run Growth:
-4
Growth Rate:
-16.67%
Total runs:
23
Run Growth:
16
Growth Rate:
69.57%