github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #1616] How to skip animation? #47410

New Issue
Closed
opened 2026-04-28 03:45:01 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-28 03:45:01 -05:00
Owner
Copy Link

Originally created by @kokizzu on GitHub (Dec 19, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1616

for example when i run:

ollama run mistral 
>>> some prompt

... very slow letter by letter output ... <-- how to make this faster?
Originally created by @kokizzu on GitHub (Dec 19, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1616 for example when i run: ``` ollama run mistral >>> some prompt ... very slow letter by letter output ... <-- how to make this faster? ```
GiteaMirror commented 2026-04-28 03:45:02 -05:00
Author
Owner
Copy Link

@igorschlum commented on GitHub (Dec 19, 2023):

hi @kokizzu it's like that when there is not enough available memory. If you are on a Mac with 8GB of RAM, try to restart and only launch Ollama and Terminal. It could be faster, but 8GB is not enough for Mistral.

<!-- gh-comment-id:1863580909 --> @igorschlum commented on GitHub (Dec 19, 2023): hi @kokizzu it's like that when there is not enough available memory. If you are on a Mac with 8GB of RAM, try to restart and only launch Ollama and Terminal. It could be faster, but 8GB is not enough for Mistral.
GiteaMirror commented 2026-04-28 03:45:03 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Dec 19, 2023):

@kokizzu what are the specs for your system? If you have a limited amount of GPU memory this would be expected behaviour.

<!-- gh-comment-id:1863627216 --> @pdevine commented on GitHub (Dec 19, 2023): @kokizzu what are the specs for your system? If you have a limited amount of GPU memory this would be expected behaviour.
GiteaMirror commented 2026-04-28 03:45:03 -05:00
Author
Owner
Copy Link

@kokizzu commented on GitHub (Dec 20, 2023):

32 core Ryzen 9 , 128GB RAM '__') but no nvidia GPU, just old AMD RX 6600 XT

<!-- gh-comment-id:1865263776 --> @kokizzu commented on GitHub (Dec 20, 2023): 32 core Ryzen 9 , 128GB RAM '__') but no nvidia GPU, just old AMD RX 6600 XT
GiteaMirror commented 2026-04-28 03:45:04 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Dec 20, 2023):

Unfortunately you are running on the CPU and it's just not very fast. The AMD support is just about to go in, but I'm not sure if that card is supported in ROCm 6. You can try it w/ PR #1146 or wait until that gets merged (hopefully later today or tomorrow).

If you are using the API (either /api/generate or /api/chat) you can set stream=false which will return everything as one response instead of token by token, but there isn't a way to do that in the REPL (i.e. the CLI).

Barring that, you can either try by renting an instance in the cloud (like on Fly.io or from Paperspace), or upgrade to a faster system. I'm going to go ahead and close the issue, but feel free to re-open it (or better, just ask on the discord) if you want to follow up.

<!-- gh-comment-id:1865285536 --> @pdevine commented on GitHub (Dec 20, 2023): Unfortunately you are running on the CPU and it's just not very fast. The AMD support is *just* about to go in, but I'm not sure if that card is supported in ROCm 6. You can try it w/ PR #1146 or wait until that gets merged (hopefully later today or tomorrow). If you are using the API (either `/api/generate` or `/api/chat`) you can set `stream=false` which will return everything as one response instead of token by token, but there isn't a way to do that in the REPL (i.e. the CLI). Barring that, you can either try by renting an instance in the cloud (like on Fly.io or from Paperspace), or upgrade to a faster system. I'm going to go ahead and close the issue, but feel free to re-open it (or better, just ask on the discord) if you want to follow up.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#47410
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?