NVIDIA connector is experiencing CRITICAL issues

### Description

The connector doesn't cover the entire list of available models, but only a small subset, which is displayed in the open code.
I wrote a small script to query the available models:

```python
import os
import sys
import requests

# Load environment variables if dotenv is available
try:
    from dotenv import load_dotenv
    load_dotenv()
except ImportError:
    pass

NGC_KEY = os.getenv('NGC_KEY')

if not NGC_KEY:
    print("Error: NGC_KEY environment variable is not set.", file=sys.stderr)
    sys.exit(1)

def fetch_models():
    url = 'https://integrate.api.nvidia.com/v1/models'
    headers = {'X-Api-Key': NGC_KEY}
    
    try:
        response = requests.get(url, headers=headers)
        response.raise_for_status()
        data = response.json()
        
        for model in data.get('data', []):
            model_id = model.get('id')
            if model_id:
                print(model_id)
                
    except requests.exceptions.RequestException as e:
        print(f"Error fetching models: {e}", file=sys.stderr)
        sys.exit(1)

if __name__ == "__main__":
    fetch_models()

```

<details>
<summary>As a result, I got the following list (spoiler)</summary>

1. 01-ai/yi-large
2. abacusai/dracarys-llama-3.1-70b-instruct
3. adept/fuyu-8b
4. ai21labs/jamba-1.5-large-instruct
5. ai21labs/jamba-1.5-mini-instruct
6. aisingapore/sea-lion-7b-instruct
7. baai/bge-m3
8. baichuan-inc/baichuan2-13b-chat
9. bigcode/starcoder2-15b
10. bigcode/starcoder2-7b
11. bytedance/seed-oss-36b-instruct
12. databricks/dbrx-instruct
13. deepseek-ai/deepseek-coder-6.7b-instruct
14. deepseek-ai/deepseek-r1-distill-llama-8b
15. deepseek-ai/deepseek-r1-distill-qwen-14b
16. deepseek-ai/deepseek-r1-distill-qwen-32b
17. deepseek-ai/deepseek-r1-distill-qwen-7b
18. deepseek-ai/deepseek-v3.1
19. deepseek-ai/deepseek-v3.1-terminus
20. deepseek-ai/deepseek-v3.2
21. google/codegemma-1.1-7b
22. google/codegemma-7b
23. google/deplot
24. google/gemma-2-27b-it
25. google/gemma-2-2b-it
26. google/gemma-2-9b-it
27. google/gemma-2b
28. google/gemma-3-12b-it
29. google/gemma-3-1b-it
30. google/gemma-3-27b-it
31. google/gemma-3-4b-it
32. google/gemma-3n-e2b-it
33. google/gemma-3n-e4b-it
34. google/gemma-7b
35. google/paligemma
36. google/recurrentgemma-2b
37. google/shieldgemma-9b
38. gotocompany/gemma-2-9b-cpt-sahabatai-instruct
39. ibm/granite-3.0-3b-a800m-instruct
40. ibm/granite-3.0-8b-instruct
41. ibm/granite-3.3-8b-instruct
42. ibm/granite-34b-code-instruct
43. ibm/granite-8b-code-instruct
44. ibm/granite-guardian-3.0-8b
45. igenius/colosseum_355b_instruct_16k
46. igenius/italia_10b_instruct_16k
47. institute-of-science-tokyo/llama-3.1-swallow-70b-instruct-v0.1
48. institute-of-science-tokyo/llama-3.1-swallow-8b-instruct-v0.1
49. marin/marin-8b-instruct
50. mediatek/breeze-7b-instruct
51. meta/codellama-70b
52. meta/llama-3.1-405b-instruct
53. meta/llama-3.1-70b-instruct
54. meta/llama-3.1-8b-instruct
55. meta/llama-3.2-11b-vision-instruct
56. meta/llama-3.2-1b-instruct
57. meta/llama-3.2-3b-instruct
58. meta/llama-3.2-90b-vision-instruct
59. meta/llama-3.3-70b-instruct
60. meta/llama-4-maverick-17b-128e-instruct
61. meta/llama-4-scout-17b-16e-instruct
62. meta/llama-guard-4-12b
63. meta/llama2-70b
64. meta/llama3-70b-instruct
65. meta/llama3-8b-instruct
66. microsoft/kosmos-2
67. microsoft/phi-3-medium-128k-instruct
68. microsoft/phi-3-medium-4k-instruct
69. microsoft/phi-3-mini-128k-instruct
70. microsoft/phi-3-mini-4k-instruct
71. microsoft/phi-3-small-128k-instruct
72. microsoft/phi-3-small-8k-instruct
73. microsoft/phi-3-vision-128k-instruct
74. microsoft/phi-3.5-mini-instruct
75. microsoft/phi-3.5-moe-instruct
76. microsoft/phi-3.5-vision-instruct
77. microsoft/phi-4-mini-flash-reasoning
78. microsoft/phi-4-mini-instruct
79. microsoft/phi-4-multimodal-instruct
80. minimaxai/minimax-m2
81. minimaxai/minimax-m2.1
82. mistralai/codestral-22b-instruct-v0.1
83. mistralai/devstral-2-123b-instruct-2512
84. mistralai/magistral-small-2506
85. mistralai/mamba-codestral-7b-v0.1
86. mistralai/mathstral-7b-v0.1
87. mistralai/ministral-14b-instruct-2512
88. mistralai/mistral-7b-instruct-v0.2
89. mistralai/mistral-7b-instruct-v0.3
90. mistralai/mistral-large
91. mistralai/mistral-large-2-instruct
92. mistralai/mistral-large-3-675b-instruct-2512
93. mistralai/mistral-medium-3-instruct
94. mistralai/mistral-nemotron
95. mistralai/mistral-small-24b-instruct
96. mistralai/mistral-small-3.1-24b-instruct-2503
97. mistralai/mixtral-8x22b-instruct-v0.1
98. mistralai/mixtral-8x22b-v0.1
99. mistralai/mixtral-8x7b-instruct-v0.1
100. moonshotai/kimi-k2-instruct
101. moonshotai/kimi-k2-instruct-0905
102. moonshotai/kimi-k2-thinking
103. moonshotai/kimi-k2.5
104. nv-mistralai/mistral-nemo-12b-instruct
105. nvidia/cosmos-reason2-8b
106. nvidia/embed-qa-4
107. nvidia/llama-3.1-nemoguard-8b-content-safety
108. nvidia/llama-3.1-nemoguard-8b-topic-control
109. nvidia/llama-3.1-nemotron-51b-instruct
110. nvidia/llama-3.1-nemotron-70b-instruct
111. nvidia/llama-3.1-nemotron-70b-reward
112. nvidia/llama-3.1-nemotron-nano-4b-v1.1
113. nvidia/llama-3.1-nemotron-nano-8b-v1
114. nvidia/llama-3.1-nemotron-nano-vl-8b-v1
115. nvidia/llama-3.1-nemotron-safety-guard-8b-v3
116. nvidia/llama-3.1-nemotron-ultra-253b-v1
117. nvidia/llama-3.2-nemoretriever-1b-vlm-embed-v1
118. nvidia/llama-3.2-nemoretriever-300m-embed-v1
119. nvidia/llama-3.2-nemoretriever-300m-embed-v2
120. nvidia/llama-3.2-nv-embedqa-1b-v1
121. nvidia/llama-3.2-nv-embedqa-1b-v2
122. nvidia/llama-3.3-nemotron-super-49b-v1
123. nvidia/llama-3.3-nemotron-super-49b-v1.5
124. nvidia/llama3-chatqa-1.5-70b
125. nvidia/llama3-chatqa-1.5-8b
126. nvidia/mistral-nemo-minitron-8b-8k-instruct
127. nvidia/mistral-nemo-minitron-8b-base
128. nvidia/nemoretriever-parse
129. nvidia/nemotron-3-nano-30b-a3b
130. nvidia/nemotron-4-340b-instruct
131. nvidia/nemotron-4-340b-reward
132. nvidia/nemotron-4-mini-hindi-4b-instruct
133. nvidia/nemotron-content-safety-reasoning-4b
134. nvidia/nemotron-mini-4b-instruct
135. nvidia/nemotron-nano-12b-v2-vl
136. nvidia/nemotron-nano-3-30b-a3b
137. nvidia/nemotron-parse
138. nvidia/neva-22b
139. nvidia/nv-embed-v1
140. nvidia/nv-embedcode-7b-v1
141. nvidia/nv-embedqa-e5-v5
142. nvidia/nv-embedqa-mistral-7b-v2
143. nvidia/nvclip
144. nvidia/nvidia-nemotron-nano-9b-v2
145. nvidia/riva-translate-4b-instruct
146. nvidia/riva-translate-4b-instruct-v1.1
147. nvidia/streampetr
148. nvidia/usdcode-llama-3.1-70b-instruct
149. nvidia/vila
150. openai/gpt-oss-120b
151. openai/gpt-oss-120b
152. openai/gpt-oss-20b
153. openai/gpt-oss-20b
154. opengpt-x/teuken-7b-instruct-commercial-v0.4
155. qwen/qwen2-7b-instruct
156. qwen/qwen2.5-7b-instruct
157. qwen/qwen2.5-coder-32b-instruct
158. qwen/qwen2.5-coder-7b-instruct
159. qwen/qwen3-235b-a22b
160. qwen/qwen3-coder-480b-a35b-instruct
161. qwen/qwen3-next-80b-a3b-instruct
162. qwen/qwen3-next-80b-a3b-thinking
163. qwen/qwq-32b
164. rakuten/rakutenai-7b-chat
165. rakuten/rakutenai-7b-instruct
166. sarvamai/sarvam-m
167. snowflake/arctic-embed-l
168. speakleash/bielik-11b-v2.3-instruct
169. speakleash/bielik-11b-v2.6-instruct
170. stockmark/stockmark-2-100b-instruct
171. thudm/chatglm3-6b
172. tiiuae/falcon3-7b-instruct
173. tokyotech-llm/llama-3-swallow-70b-instruct-v0.1
174. upstage/solar-10.7b-instruct
175. utter-project/eurollm-9b-instruct
176. writer/palmyra-creative-122b
177. writer/palmyra-fin-70b-32k
178. writer/palmyra-med-70b
179. writer/palmyra-med-70b-32k
180. yentinglin/llama-3-taiwan-70b-instruct
181. z-ai/glm4.7
182. zyphra/zamba2-7b-instruct

</details>

Yes, not all of them support text input, for example nvidia/nemotron-parse, but nevertheless I surveyed each of the models and based on the survey results
<details>
<summary>received successful responses from 116 models. (spoiler)</summary>

abacusai/dracarys-llama-3.1-70b-instruct: 1.24s
ai21labs/jamba-1.5-mini-instruct: 1.24s
deepseek-ai/deepseek-r1-distill-qwen-7b: 1.42s
deepseek-ai/deepseek-r1-distill-qwen-14b: 1.70s
google/gemma-3-1b-it: 0.85s
bytedance/seed-oss-36b-instruct: 2.11s
google/gemma-2-2b-it: 1.42s
google/paligemma: Error: 500 (0.97s)
google/shieldgemma-9b: 0.85s
google/gemma-2-27b-it: 1.85s
google/gemma-2-9b-it: 1.89s
google/gemma-3-27b-it: 1.64s
baichuan-inc/baichuan2-13b-chat: 2.99s
gotocompany/gemma-2-9b-cpt-sahabatai-instruct: 1.17s
google/gemma-7b: 2.04s
ibm/granite-guardian-3.0-8b: 0.99s
igenius/italia_10b_instruct_16k: 0.92s
institute-of-science-tokyo/llama-3.1-swallow-70b-instruct-v0.1: 1.07s
institute-of-science-tokyo/llama-3.1-swallow-8b-instruct-v0.1: 1.05s
google/gemma-3n-e2b-it: 2.89s
deepseek-ai/deepseek-v3.1: 4.17s
marin/marin-8b-instruct: 1.31s
mediatek/breeze-7b-instruct: 1.39s
meta/llama-3.2-1b-instruct: 0.77s
meta/llama-3.2-3b-instruct: 0.66s
meta/llama-3.1-8b-instruct: 1.06s
ibm/granite-3.3-8b-instruct: 2.18s
google/gemma-3n-e4b-it: 3.48s
meta/llama-3.1-70b-instruct: 1.35s
meta/llama-3.1-405b-instruct: 1.79s
igenius/colosseum_355b_instruct_16k: 2.45s
meta/llama-4-scout-17b-16e-instruct: 0.67s
meta/llama-guard-4-12b: 0.67s
meta/llama-4-maverick-17b-128e-instruct: 1.13s
meta/llama-3.2-11b-vision-instruct: 1.75s
meta/llama-3.2-90b-vision-instruct: 1.52s
meta/llama-3.3-70b-instruct: 1.47s
meta/llama3-8b-instruct: 1.20s
google/gemma-3-4b-it: 4.75s
meta/llama3-70b-instruct: 1.79s
microsoft/phi-3-small-128k-instruct: 1.33s
microsoft/phi-3-medium-4k-instruct: 1.61s
microsoft/phi-3-mini-4k-instruct: 1.51s
microsoft/phi-3.5-vision-instruct: 1.03s
microsoft/phi-3-small-8k-instruct: 1.59s
microsoft/phi-4-mini-flash-reasoning: 1.28s
microsoft/phi-3-mini-128k-instruct: 2.04s
microsoft/phi-3.5-mini-instruct: 1.93s
minimaxai/minimax-m2: 1.58s
google/gemma-3-12b-it: 6.65s
microsoft/phi-3-medium-128k-instruct: 2.96s
mistralai/ministral-14b-instruct-2512: 1.33s
minimaxai/minimax-m2.1: 2.06s
mistralai/mathstral-7b-v0.1: 1.54s
mistralai/mistral-7b-instruct-v0.2: 1.50s
mistralai/mistral-7b-instruct-v0.3: 1.72s
mistralai/mamba-codestral-7b-v0.1: 2.03s
mistralai/devstral-2-123b-instruct-2512: 2.30s
mistralai/magistral-small-2506: 2.33s
moonshotai/kimi-k2-instruct: 1.25s
mistralai/mistral-nemotron: 1.96s
mistralai/mixtral-8x7b-instruct-v0.1: 1.51s
moonshotai/kimi-k2-instruct-0905: 1.38s
mistralai/mistral-medium-3-instruct: 2.22s
mistralai/mixtral-8x22b-instruct-v0.1: 1.91s
moonshotai/kimi-k2-thinking: 1.54s
nvidia/llama-3.1-nemoguard-8b-topic-control: 0.64s
nvidia/llama-3.1-nemoguard-8b-content-safety: 0.81s
mistralai/mistral-small-24b-instruct: 2.54s
mistralai/mistral-small-3.1-24b-instruct-2503: 2.58s
nvidia/llama-3.1-nemotron-safety-guard-8b-v3: 0.70s
nvidia/llama-3.1-nemotron-nano-4b-v1.1: 1.25s
nvidia/llama-3.1-nemotron-nano-vl-8b-v1: 1.34s
nvidia/llama-3.1-nemotron-nano-8b-v1: 1.43s
nvidia/llama3-chatqa-1.5-8b: 0.89s
nvidia/llama-3.1-nemotron-70b-reward: 1.98s
nvidia/nemoretriever-parse: Error: 400 (0.80s)
nvidia/llama-3.1-nemotron-ultra-253b-v1: 1.87s
nvidia/nemotron-3-nano-30b-a3b: 1.12s
nvidia/nemotron-content-safety-reasoning-4b: 0.87s
nvidia/nemotron-4-mini-hindi-4b-instruct: 1.12s
nvidia/nemotron-mini-4b-instruct: 1.10s
nvidia/nemotron-parse: Error: 400 (0.87s)
nvidia/llama-3.3-nemotron-super-49b-v1.5: 2.20s
nvidia/llama-3.3-nemotron-super-49b-v1: 2.29s
nvidia/nemotron-nano-12b-v2-vl: 1.50s
openai/gpt-oss-20b: 0.80s
openai/gpt-oss-120b: 1.03s
openai/gpt-oss-120b: 1.22s
nvidia/riva-translate-4b-instruct-v1.1: 1.30s
openai/gpt-oss-20b: 1.22s
qwen/qwen2-7b-instruct: 1.20s
qwen/qwen2.5-7b-instruct: 1.23s
qwen/qwen2.5-coder-7b-instruct: 0.97s
opengpt-x/teuken-7b-instruct-commercial-v0.4: 1.80s
qwen/qwen3-235b-a22b: 1.84s
qwen/qwen2.5-coder-32b-instruct: 2.22s
rakuten/rakutenai-7b-instruct: 1.67s
rakuten/rakutenai-7b-chat: 2.02s
nvidia/usdcode-llama-3.1-70b-instruct: 4.11s
sarvamai/sarvam-m: 2.27s
speakleash/bielik-11b-v2.3-instruct: 1.62s
moonshotai/kimi-k2.5: 8.52s
deepseek-ai/deepseek-v3.1-terminus: 17.10s
speakleash/bielik-11b-v2.6-instruct: 2.17s
qwen/qwen3-coder-480b-a35b-instruct: 3.95s
thudm/chatglm3-6b: 1.57s
tiiuae/falcon3-7b-instruct: 1.33s
stockmark/stockmark-2-100b-instruct: 2.66s
utter-project/eurollm-9b-instruct: 1.44s
upstage/solar-10.7b-instruct: 2.36s
tokyotech-llm/llama-3-swallow-70b-instruct-v0.1: 3.24s
yentinglin/llama-3-taiwan-70b-instruct: 2.37s
nvidia/nvidia-nemotron-nano-9b-v2: 9.11s
z-ai/glm4.7: 26.84s
microsoft/phi-4-multimodal-instruct: 58.71s
qwen/qwen3-next-80b-a3b-thinking: 183.53s
qwen/qwen3-next-80b-a3b-instruct: 266.68s
mistralai/mistral-large-3-675b-instruct-2512: 293.33s
deepseek-ai/deepseek-r1-distill-llama-8b: Error: Timeout (300.00s)
deepseek-ai/deepseek-v3.2: Error: Timeout (300.00s)
deepseek-ai/deepseek-r1-distill-qwen-32b: Error: Timeout (300.00s)
microsoft/phi-4-mini-instruct: Error: Timeout (300.00s)
qwen/qwq-32b: Error: Timeout (300.00s)
</details>

Yes, large models like the Qwen3 and DeepSeek R1 didn't respond and were timed out, but the very high-quality GLM model did respond. If you select the GLM model in the open code, it simply doesn't respond, although I personally verified that it works fine using the API.

I urge you to look into this issue, as this connector is a gem in vibe coding.

I also found a problem with some llama models in opencode, instead of calling tools they send a <tool_call> message and this is not handled in any way:

> Check file VERSION.md
> 11:33 PM
> Thinking: Okay, the user wants me to check the contents of the VERSION.md file. Let me start by recalling the available tools. The 'read' tool is used to read files from the local filesystem. The parameters require an absolute file path. Since the user mentioned VERSION.md, I need to confirm the absolute path.
> Looking at the environment details, the working directory is /home/albert/Desktop/mytest. So the absolute path would be /home/albert/Desktop/mytest/VERSION.md. I should use the read tool with this file path. There's no mention of needing offset or limit, so I'll omit those parameters. Let me make sure that the file exists. Wait, the user didn't specify, but the read tool can handle non-existent files by returning an error. But since the user is asking to check it, it's likely that the file exists. I'll proceed to call the read tool with the specified path.
> <tool_call>
> {"name": "read", "arguments": {"filePath": "/home/user/mytest/VERSION.md"}}
> </tool_call>

Due to this critical issue, the model becomes completely unsuitable for any interaction, since it can only effectively respond in text.

### Plugins

none

### OpenCode version

1.1.36

### Steps to reproduce

_No response_

### Screenshot and/or share link

_No response_

### Operating System

Linux Mint 22.1 x86_64

### Terminal

gnome-terminal / bash 5.2.21

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

NVIDIA connector is experiencing CRITICAL issues #10885

Description

Plugins

OpenCode version

Steps to reproduce

Screenshot and/or share link

Operating System

Terminal

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

NVIDIA connector is experiencing CRITICAL issues #10885

Description

Description

Plugins

OpenCode version

Steps to reproduce

Screenshot and/or share link

Operating System

Terminal

Metadata

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

Issue actions