github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 08:02:14 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #13107] AIMAX395 with ROCM 7.0.2 have a wrong VRAM size. #8678

New Issue
Closed
opened 2026-04-12 21:26:46 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-12 21:26:46 -05:00
Owner
Copy Link

Originally created by @zaryalyu on GitHub (Nov 16, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/13107

What is the issue?

I have a AIMAX 395 with ROCM 7.0.2.And I set it VRAM to 96GB but it only have 15.5 GiB available so I can't running something bigger than that.So what would I do?

Relevant log output

ollama serve:
time=2025-11-16T20:56:48.174+08:00 level=INFO source=routes.go:1544 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/home/zarya/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
time=2025-11-16T20:56:48.175+08:00 level=INFO source=images.go:522 msg="total blobs: 15"
time=2025-11-16T20:56:48.175+08:00 level=INFO source=images.go:529 msg="total unused blobs removed: 0"
time=2025-11-16T20:56:48.175+08:00 level=INFO source=routes.go:1597 msg="Listening on 127.0.0.1:11434 (version 0.12.11)"
time=2025-11-16T20:56:48.176+08:00 level=INFO source=runner.go:67 msg="discovering available GPUs..."
time=2025-11-16T20:56:48.176+08:00 level=INFO source=server.go:392 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 37161"
time=2025-11-16T20:56:48.191+08:00 level=INFO source=server.go:392 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 36393"
time=2025-11-16T20:56:48.206+08:00 level=INFO source=server.go:392 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 38317"
time=2025-11-16T20:56:48.602+08:00 level=INFO source=server.go:392 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 32895"
time=2025-11-16T20:56:49.091+08:00 level=INFO source=types.go:42 msg="inference compute" id=0 filter_id=0 library=ROCm compute=gfx1151 name=ROCm0 description="AMD Radeon Graphics" libdirs=ollama,rocm driver=60342.13 pci_id=0000:c6:00.0 type=iGPU total="15.5 GiB" available="15.3 GiB"
time=2025-11-16T20:56:49.091+08:00 level=INFO source=routes.go:1638 msg="entering low vram mode" "total vram"="15.5 GiB" threshold="20.0 GiB"
cat /opt/rocm/.info/version
7.0.2

OS

Linux

GPU

AMD

CPU

AMD

Ollama version

0.12.11

Originally created by @zaryalyu on GitHub (Nov 16, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/13107 ### What is the issue? I have a AIMAX 395 with ROCM 7.0.2.And I set it VRAM to 96GB but it only have 15.5 GiB available so I can't running something bigger than that.So what would I do? ### Relevant log output ```shell ollama serve: time=2025-11-16T20:56:48.174+08:00 level=INFO source=routes.go:1544 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/home/zarya/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" time=2025-11-16T20:56:48.175+08:00 level=INFO source=images.go:522 msg="total blobs: 15" time=2025-11-16T20:56:48.175+08:00 level=INFO source=images.go:529 msg="total unused blobs removed: 0" time=2025-11-16T20:56:48.175+08:00 level=INFO source=routes.go:1597 msg="Listening on 127.0.0.1:11434 (version 0.12.11)" time=2025-11-16T20:56:48.176+08:00 level=INFO source=runner.go:67 msg="discovering available GPUs..." time=2025-11-16T20:56:48.176+08:00 level=INFO source=server.go:392 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 37161" time=2025-11-16T20:56:48.191+08:00 level=INFO source=server.go:392 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 36393" time=2025-11-16T20:56:48.206+08:00 level=INFO source=server.go:392 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 38317" time=2025-11-16T20:56:48.602+08:00 level=INFO source=server.go:392 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 32895" time=2025-11-16T20:56:49.091+08:00 level=INFO source=types.go:42 msg="inference compute" id=0 filter_id=0 library=ROCm compute=gfx1151 name=ROCm0 description="AMD Radeon Graphics" libdirs=ollama,rocm driver=60342.13 pci_id=0000:c6:00.0 type=iGPU total="15.5 GiB" available="15.3 GiB" time=2025-11-16T20:56:49.091+08:00 level=INFO source=routes.go:1638 msg="entering low vram mode" "total vram"="15.5 GiB" threshold="20.0 GiB" cat /opt/rocm/.info/version 7.0.2 ``` ### OS Linux ### GPU AMD ### CPU AMD ### Ollama version 0.12.11
GiteaMirror added the bug label 2026-04-12 21:26:46 -05:00
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#8678
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?