github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #9725] 升级到ollama0.6.0无法使用 #52868

New Issue
Closed
opened 2026-04-29 01:14:11 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-29 01:14:11 -05:00
Owner
Copy Link

Originally created by @shaken154 on GitHub (Mar 13, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9725

What is the issue?

在win10专业工作站版系统上，内存D5 192G和显卡RTX2080TI22G，CUDA12.4，升级到ollama0.6.0无法使用。

Relevant log output

PowerShell 7.5.0
PS C:\Users\Administrator> ollama ls
NAME                                                          ID              SIZE      MODIFIED
gemma3:27b-it-fp16                                            cf10306fe9c6    54 GB     10 hours ago
gemma3:27b                                                    30ddded7fba6    17 GB     10 hours ago
minicpm-v:8b-2.6-fp16                                         f3f122c78635    16 GB     3 weeks ago
huihui_ai/qwen2.5-abliterate:32b-instruct-q8_0                861f54f56f44    34 GB     3 weeks ago
huihui_ai/deepseek-r1-abliterated:70b-llama-distill-q4_K_M    50f8d0fe980f    42 GB     3 weeks ago
huihui_ai/deepseek-r1-abliterated:14b-qwen-distill-q4_K_M     6b2209ffd758    9.0 GB    3 weeks ago
huihui_ai/qwen2.5-coder-abliterate:32b-instruct-q8_0          e6c35f06e4c4    34 GB     3 weeks ago
huihui_ai/deepseek-r1-abliterated:70b-llama-distill-fp16      1e86280674d4    141 GB    3 weeks ago
huihui_ai/deepseek-r1-abliterated:32b-qwen-distill-fp16       9f2aa8dff7c5    65 GB     3 weeks ago
bartowski/DeepSeek-V2.5-Q5_K_M-cu124-GPU22G:latest            fe098c5671ef    167 GB    3 weeks ago
DeepSeek-R1-671b-1.73bit-GPU22G:latest                        0a068073192a    168 GB    4 weeks ago
qwen2:72b-text-q4_K_M                                         395e2f1e4576    47 GB     4 weeks ago
deepseek-coder-v2:236b                                        c78d80129305    132 GB    4 weeks ago
bge-m3:latest                                                 790764642607    1.2 GB    4 weeks ago
nemotron:70b                                                  2262f047a28a    42 GB     4 weeks ago
medllama2:7b-q8_0                                             1bc066950c7a    7.2 GB    4 weeks ago
nomic-embed-text:latest                                       0a109f422b47    274 MB    5 weeks ago
qwen2.5:7b                                                    845dbda0ea48    4.7 GB    5 weeks ago
PS C:\Users\Administrator> ollama run gemma3:27b
>>> 你是？
Error: POST predict: Post "http://127.0.0.1:9390/completion": read tcp 127.0.0.1:9392->127.0.0.1:9390: wsarecv: An existing connection was forcibly closed by the remote host.
PS C:\Users\Administrator> ollama ps
NAME          ID              SIZE     PROCESSOR    UNTIL
gemma3:27b    30ddded7fba6    18 GB    100% GPU     Forever
PS C:\Users\Administrator> ollama stop gemma3:27b
PS C:\Users\Administrator> ollama ps
NAME    ID    SIZE    PROCESSOR    UNTIL
PS C:\Users\Administrator> ollama run qwen2.5:7b
Error: llama runner process has terminated: GGML_ASSERT(tensor->op == GGML_OP_UNARY) failed
PS C:\Users\Administrator>

OS

Windows

GPU

Intel, Nvidia

CPU

Intel

Ollama version

0.6.0

Originally created by @shaken154 on GitHub (Mar 13, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9725 ### What is the issue? 在win10专业工作站版系统上，内存D5 192G和显卡RTX2080TI22G，CUDA12.4，升级到ollama0.6.0无法使用。 ### Relevant log output ```shell PowerShell 7.5.0 PS C:\Users\Administrator> ollama ls NAME ID SIZE MODIFIED gemma3:27b-it-fp16 cf10306fe9c6 54 GB 10 hours ago gemma3:27b 30ddded7fba6 17 GB 10 hours ago minicpm-v:8b-2.6-fp16 f3f122c78635 16 GB 3 weeks ago huihui_ai/qwen2.5-abliterate:32b-instruct-q8_0 861f54f56f44 34 GB 3 weeks ago huihui_ai/deepseek-r1-abliterated:70b-llama-distill-q4_K_M 50f8d0fe980f 42 GB 3 weeks ago huihui_ai/deepseek-r1-abliterated:14b-qwen-distill-q4_K_M 6b2209ffd758 9.0 GB 3 weeks ago huihui_ai/qwen2.5-coder-abliterate:32b-instruct-q8_0 e6c35f06e4c4 34 GB 3 weeks ago huihui_ai/deepseek-r1-abliterated:70b-llama-distill-fp16 1e86280674d4 141 GB 3 weeks ago huihui_ai/deepseek-r1-abliterated:32b-qwen-distill-fp16 9f2aa8dff7c5 65 GB 3 weeks ago bartowski/DeepSeek-V2.5-Q5_K_M-cu124-GPU22G:latest fe098c5671ef 167 GB 3 weeks ago DeepSeek-R1-671b-1.73bit-GPU22G:latest 0a068073192a 168 GB 4 weeks ago qwen2:72b-text-q4_K_M 395e2f1e4576 47 GB 4 weeks ago deepseek-coder-v2:236b c78d80129305 132 GB 4 weeks ago bge-m3:latest 790764642607 1.2 GB 4 weeks ago nemotron:70b 2262f047a28a 42 GB 4 weeks ago medllama2:7b-q8_0 1bc066950c7a 7.2 GB 4 weeks ago nomic-embed-text:latest 0a109f422b47 274 MB 5 weeks ago qwen2.5:7b 845dbda0ea48 4.7 GB 5 weeks ago PS C:\Users\Administrator> ollama run gemma3:27b >>> 你是？ Error: POST predict: Post "http://127.0.0.1:9390/completion": read tcp 127.0.0.1:9392->127.0.0.1:9390: wsarecv: An existing connection was forcibly closed by the remote host. PS C:\Users\Administrator> ollama ps NAME ID SIZE PROCESSOR UNTIL gemma3:27b 30ddded7fba6 18 GB 100% GPU Forever PS C:\Users\Administrator> ollama stop gemma3:27b PS C:\Users\Administrator> ollama ps NAME ID SIZE PROCESSOR UNTIL PS C:\Users\Administrator> ollama run qwen2.5:7b Error: llama runner process has terminated: GGML_ASSERT(tensor->op == GGML_OP_UNARY) failed PS C:\Users\Administrator> ``` ### OS Windows ### GPU Intel, Nvidia ### CPU Intel ### Ollama version 0.6.0
GiteaMirror added the bug label 2026-04-29 01:14:11 -05:00
GiteaMirror commented 2026-04-29 01:14:14 -05:00
Author
Owner
Copy Link

@shaken154 commented on GitHub (Mar 13, 2025):

版本退回0.5.13，qwen2.5:7b还是用不了，决定不用ollama了，转用LM Studio，这个非常稳定。

<!-- gh-comment-id:2720876000 --> @shaken154 commented on GitHub (Mar 13, 2025): 版本退回0.5.13，qwen2.5:7b还是用不了，决定不用ollama了，转用LM Studio，这个非常稳定。
GiteaMirror commented 2026-04-29 01:14:15 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 13, 2025):

#9509

<!-- gh-comment-id:2720900845 --> @rick-github commented on GitHub (Mar 13, 2025): #9509
GiteaMirror commented 2026-04-29 01:14:16 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Mar 14, 2025):

Going to close this as a dupe.

<!-- gh-comment-id:2725892121 --> @pdevine commented on GitHub (Mar 14, 2025): Going to close this as a dupe.
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 bug
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#52868
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?