Skip to content

Add gemma 4 31b and deepseek v4 flash to neuralwatt #3795

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
amitksingh1490 merged 2 commits into from
Jul 31, 2026
+20 −20
Merged

Add gemma 4 31b and deepseek v4 flash to neuralwatt #3795

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
68d7a02
Add gemma 4 31b and deepseek v4 flash to neuralwatt
jonathan-s Jul 31, 2026
0c26dc0
Merge branch 'main' into neuralwatt
amitksingh1490 Jul 31, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
40 changes: 20 additions & 20 deletions crates/forge_repo/src/provider/provider.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1028,26 +1028,6 @@
"supports_reasoning": true,
"input_modalities": ["text", "image"]
},
{
"id": "kimi-k2.5",
"name": "Kimi K2.5",
"description": "Kimi K2.5 — quant-agnostic canonical name for the Kimi K2.5 family.",
"context_length": 262128,
"tools_supported": true,
"supports_parallel_tool_calls": true,
"supports_reasoning": true,
"input_modalities": ["text", "image"]
},
{
"id": "kimi-k2.5-fast",
"name": "Kimi K2.5 Fast",
"description": "Moonshot Kimi K2.5 with thinking mode disabled for instant, lower-latency responses.",
"context_length": 262128,
"tools_supported": true,
"supports_parallel_tool_calls": true,
"supports_reasoning": false,
"input_modalities": ["text", "image"]
},
{
"id": "qwen3.6-35b",
"name": "Qwen3.6 35B",
Expand Down Expand Up @@ -1137,6 +1117,26 @@
"supports_parallel_tool_calls": true,
"supports_reasoning": false,
"input_modalities": ["text"]
},
{
"id": "deepseek-v4-flash",
"name": "DeepSeek V4 Flash",
"description": "DeepSeek V4 Flash — MoE with DSpark speculative decoding, native 1M context, served on 4x B200.",
"context_length": 1048576,
"tools_supported": true,
"supports_parallel_tool_calls": true,
"supports_reasoning": true,
"input_modalities": ["text"]
},
{
"id": "gemma-4-31b",
"name": "Gemma 4 31B",
"description": "Google Gemma 4 31B — multimodal (text + vision) with tool calling and 262K context.",
"context_length": 262144,
"tools_supported": true,
"supports_parallel_tool_calls": true,
"supports_reasoning": false,
"input_modalities": ["text", "image"]
}
],
"auth_methods": ["api_key"]
Expand Down
Loading