[GH-ISSUE #11214] Warning when using nomic-embed-text:v1.5 with default 8192 context #33147

Open
opened 2026-04-22 15:33:42 -05:00 by GiteaMirror · 0 comments
Owner

Originally created by @TomatoCo on GitHub (Jun 27, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11214

What is the issue?

nomic-embed-text:v1.5 is configured to use a context length of 8192. Nomic's documentation says that this is a supported configuration.

In ollama 0.9.0 it can use up to 8192. In ollama 0.9.3 it logs
time=2025-06-27T01:23:48.232Z level=WARN source=server.go:145 msg="requested context size too large for model" num_ctx=8192 num_parallel=1 n_ctx_train=2048
and later logs
llama_context: n_ctx = 2048
llama_context: n_ctx_per_seq = 2048

Did this ever work? Are there plans to (re)add this functionality?

OS

Ubuntu 24.04 LTS

GPU

None

CPU

AMD 7700X

Ollama version

0.9.3

Originally created by @TomatoCo on GitHub (Jun 27, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11214 ### What is the issue? nomic-embed-text:v1.5 is configured to use a context length of 8192. Nomic's documentation says that this is a supported configuration. In ollama 0.9.0 it can use up to 8192. In ollama 0.9.3 it logs `time=2025-06-27T01:23:48.232Z level=WARN source=server.go:145 msg="requested context size too large for model" num_ctx=8192 num_parallel=1 n_ctx_train=2048` and later logs `llama_context: n_ctx = 2048` `llama_context: n_ctx_per_seq = 2048` Did this ever work? Are there plans to (re)add this functionality? ### OS Ubuntu 24.04 LTS ### GPU None ### CPU AMD 7700X ### Ollama version 0.9.3
GiteaMirror added the bug label 2026-04-22 15:33:42 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#33147