How fast is Qwen3.8 on AxForge?
How fast is Qwen3.8 on AxForge?
Solved Qwen3.8 27B
qwen3.8-27b-nvfp4
- Views
- 0
- Replies
- 3
- Created
- 2026-07-02 12:00
- Last reply
- 2026-07-02 18:21
AxForge currently cites a community GB10 result of about 25.1 tokens/s for Qwen3.8 27B NVFP4 + MTP at 4k context.
That is not the same thing as a guaranteed serverless API speed, and AxForge explicitly says it has not published its own tuned number yet.
Real speed changes with prompt length, concurrency, serving engine and batching, so I would not turn 25.1 t/s into an SLA.
Sign in to reply.
Posting guidelines
- Be helpful and respectful
- Search before you post
- Use a clear title and tags
- Add code or a screenshot when it helps
- Keep to the topic
Accounts that break these can lose forum access — paid plans included. Read the full guidelines →
Related topics
- Model requests — ask for a model we don't have yet 0 replies · 2 views
- Request: Qwen3 30B A3B 0 replies · 2 views
- Request: LTX-Video 0 replies · 2 views
- Request: MiniMax H3 0 replies · 2 views
- How much context does Qwen3.8 have on AxForge? 2 replies · 1 views