github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 00:51:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #734] Need an option with low memory of GPU #62380

New Issue
Closed
opened 2026-05-03 08:32:43 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-05-03 08:32:43 -05:00
Owner
Copy Link

Originally created by @tacsotai on GitHub (Oct 8, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/734

I tried your great program "ollama".
I was succeeded with CPU, but unfortunately my linux machine not have enough memory.
So, could you prepare an option with low memory of GPU ?

$ ollama serve
2023/10/08 06:05:12 images.go:996: total blobs: 17
2023/10/08 06:05:12 images.go:1003: total unused blobs removed: 0
2023/10/08 06:05:12 routes.go:572: Listening on 127.0.0.1:11434
2023/10/08 06:05:44 llama.go:239: 6144 MiB VRAM available, loading up to 54 GPU layers
2023/10/08 06:05:44 llama.go:313: starting llama runner
2023/10/08 06:05:44 llama.go:349: waiting for llama runner to start responding
ggml_init_cublas: found 1 CUDA devices:
  Device 0: NVIDIA GeForce RTX 3060 Laptop GPU, compute capability 8.6
{"timestamp":1696745144,"level":"INFO","function":"main","line":1190,"message":"build info","build":1009,"commit":"9e232f0"}
{"timestamp":1696745144,"level":"INFO","function":"main","line":1192,"message":"system info","n_threads":6,"total_threads":12,"system_info":"AVX = 1 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | VSX = 0 | "}
llama.cpp: loading model from /home/tac/.ollama/models/blobs/sha256:b5749cc827d33b7cb4c8869cede7b296a0a28d9e5d1982705c2ba4c603258159
llama_model_load_internal: format     = ggjt v3 (latest)
llama_model_load_internal: n_vocab    = 32000
llama_model_load_internal: n_ctx      = 2048
llama_model_load_internal: n_embd     = 4096
llama_model_load_internal: n_mult     = 256
llama_model_load_internal: n_head     = 32
llama_model_load_internal: n_head_kv  = 32
llama_model_load_internal: n_layer    = 32
llama_model_load_internal: n_rot      = 128
llama_model_load_internal: n_gqa      = 1
llama_model_load_internal: rnorm_eps  = 5.0e-06
llama_model_load_internal: n_ff       = 11008
llama_model_load_internal: freq_base  = 10000.0
llama_model_load_internal: freq_scale = 1
llama_model_load_internal: ftype      = 2 (mostly Q4_0)
llama_model_load_internal: model size = 7B
llama_model_load_internal: ggml ctx size =    0.08 MB
llama_model_load_internal: using CUDA for GPU acceleration
llama_model_load_internal: mem required  =  468.40 MB (+ 1024.00 MB per state)
llama_model_load_internal: allocating batch_size x (512 kB + n_ctx x 128 B) = 384 MB VRAM for the scratch buffer
llama_model_load_internal: offloading 32 repeating layers to GPU
llama_model_load_internal: offloading non-repeating layers to GPU
llama_model_load_internal: offloading v cache to GPU
llama_model_load_internal: offloading k cache to GPU
llama_model_load_internal: offloaded 35/35 layers to GPU
llama_model_load_internal: total VRAM used: 4954 MB
llama_new_context_with_model: kv self size  = 1024.00 MB

llama server listening at http://127.0.0.1:52159

{"timestamp":1696745144,"level":"INFO","function":"main","line":1443,"message":"HTTP server listening","hostname":"127.0.0.1","port":52159}
{"timestamp":1696745144,"level":"INFO","function":"log_server_request","line":1157,"message":"request","remote_addr":"127.0.0.1","remote_port":51346,"status":200,"method":"HEAD","path":"/","params":{}}
2023/10/08 06:05:44 llama.go:365: llama runner started in 0.802513 seconds
{"timestamp":1696745144,"level":"INFO","function":"log_server_request","line":1157,"message":"request","remote_addr":"127.0.0.1","remote_port":51346,"status":200,"method":"POST","path":"/tokenize","params":{}}
{"timestamp":1696745145,"level":"INFO","function":"log_server_request","line":1157,"message":"request","remote_addr":"127.0.0.1","remote_port":51346,"status":200,"method":"POST","path":"/tokenize","params":{}}
CUDA error 2 at /go/src/github.com/jmorganca/ollama/llm/llama.cpp/ggml/ggml-cuda.cu:4856: out of memory
[GIN] 2023/10/08 - 06:05:45 | 200 |  2.741464312s |       127.0.0.1 | POST     "/api/generate"
2023/10/08 06:05:45 llama.go:323: llama runner exited with error: exit status 1

$ nvidia-smi
Sun Oct  8 06:04:18 2023
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 535.104.12             Driver Version: 535.104.12   CUDA Version: 12.2     |
|-----------------------------------------+----------------------+----------------------+
| GPU  Name                 Persistence-M | Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf          Pwr:Usage/Cap |         Memory-Usage | GPU-Util  Compute M. |
|                                         |                      |               MIG M. |
|=========================================+======================+======================|
|   0  NVIDIA GeForce RTX 3060 ...    On  | 00000000:01:00.0 Off |                  N/A |
| N/A   38C    P0              N/A /  80W |      2MiB /  6144MiB |      0%      Default |
|                                         |                      |                  N/A |
+-----------------------------------------+----------------------+----------------------+

+---------------------------------------------------------------------------------------+
| Processes:                                                                            |
|  GPU   GI   CI        PID   Type   Process name                            GPU Memory |
|        ID   ID                                                             Usage      |
|=======================================================================================|
|  No running processes found                                                           |
+---------------------------------------------------------------------------------------+
Originally created by @tacsotai on GitHub (Oct 8, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/734 I tried your great program "ollama". I was succeeded with CPU, but unfortunately my linux machine not have enough memory. So, could you prepare an option with low memory of GPU ? ``` $ ollama serve 2023/10/08 06:05:12 images.go:996: total blobs: 17 2023/10/08 06:05:12 images.go:1003: total unused blobs removed: 0 2023/10/08 06:05:12 routes.go:572: Listening on 127.0.0.1:11434 2023/10/08 06:05:44 llama.go:239: 6144 MiB VRAM available, loading up to 54 GPU layers 2023/10/08 06:05:44 llama.go:313: starting llama runner 2023/10/08 06:05:44 llama.go:349: waiting for llama runner to start responding ggml_init_cublas: found 1 CUDA devices: Device 0: NVIDIA GeForce RTX 3060 Laptop GPU, compute capability 8.6 {"timestamp":1696745144,"level":"INFO","function":"main","line":1190,"message":"build info","build":1009,"commit":"9e232f0"} {"timestamp":1696745144,"level":"INFO","function":"main","line":1192,"message":"system info","n_threads":6,"total_threads":12,"system_info":"AVX = 1 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | VSX = 0 | "} llama.cpp: loading model from /home/tac/.ollama/models/blobs/sha256:b5749cc827d33b7cb4c8869cede7b296a0a28d9e5d1982705c2ba4c603258159 llama_model_load_internal: format = ggjt v3 (latest) llama_model_load_internal: n_vocab = 32000 llama_model_load_internal: n_ctx = 2048 llama_model_load_internal: n_embd = 4096 llama_model_load_internal: n_mult = 256 llama_model_load_internal: n_head = 32 llama_model_load_internal: n_head_kv = 32 llama_model_load_internal: n_layer = 32 llama_model_load_internal: n_rot = 128 llama_model_load_internal: n_gqa = 1 llama_model_load_internal: rnorm_eps = 5.0e-06 llama_model_load_internal: n_ff = 11008 llama_model_load_internal: freq_base = 10000.0 llama_model_load_internal: freq_scale = 1 llama_model_load_internal: ftype = 2 (mostly Q4_0) llama_model_load_internal: model size = 7B llama_model_load_internal: ggml ctx size = 0.08 MB llama_model_load_internal: using CUDA for GPU acceleration llama_model_load_internal: mem required = 468.40 MB (+ 1024.00 MB per state) llama_model_load_internal: allocating batch_size x (512 kB + n_ctx x 128 B) = 384 MB VRAM for the scratch buffer llama_model_load_internal: offloading 32 repeating layers to GPU llama_model_load_internal: offloading non-repeating layers to GPU llama_model_load_internal: offloading v cache to GPU llama_model_load_internal: offloading k cache to GPU llama_model_load_internal: offloaded 35/35 layers to GPU llama_model_load_internal: total VRAM used: 4954 MB llama_new_context_with_model: kv self size = 1024.00 MB llama server listening at http://127.0.0.1:52159 {"timestamp":1696745144,"level":"INFO","function":"main","line":1443,"message":"HTTP server listening","hostname":"127.0.0.1","port":52159} {"timestamp":1696745144,"level":"INFO","function":"log_server_request","line":1157,"message":"request","remote_addr":"127.0.0.1","remote_port":51346,"status":200,"method":"HEAD","path":"/","params":{}} 2023/10/08 06:05:44 llama.go:365: llama runner started in 0.802513 seconds {"timestamp":1696745144,"level":"INFO","function":"log_server_request","line":1157,"message":"request","remote_addr":"127.0.0.1","remote_port":51346,"status":200,"method":"POST","path":"/tokenize","params":{}} {"timestamp":1696745145,"level":"INFO","function":"log_server_request","line":1157,"message":"request","remote_addr":"127.0.0.1","remote_port":51346,"status":200,"method":"POST","path":"/tokenize","params":{}} CUDA error 2 at /go/src/github.com/jmorganca/ollama/llm/llama.cpp/ggml/ggml-cuda.cu:4856: out of memory [GIN] 2023/10/08 - 06:05:45 | 200 | 2.741464312s | 127.0.0.1 | POST "/api/generate" 2023/10/08 06:05:45 llama.go:323: llama runner exited with error: exit status 1 ``` ``` $ nvidia-smi Sun Oct 8 06:04:18 2023 +---------------------------------------------------------------------------------------+ | NVIDIA-SMI 535.104.12 Driver Version: 535.104.12 CUDA Version: 12.2 | |-----------------------------------------+----------------------+----------------------+ | GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |=========================================+======================+======================| | 0 NVIDIA GeForce RTX 3060 ... On | 00000000:01:00.0 Off | N/A | | N/A 38C P0 N/A / 80W | 2MiB / 6144MiB | 0% Default | | | | N/A | +-----------------------------------------+----------------------+----------------------+ +---------------------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=======================================================================================| | No running processes found | +---------------------------------------------------------------------------------------+ ```
GiteaMirror commented 2026-05-03 08:32:45 -05:00
Author
Owner
Copy Link

@tacsotai commented on GitHub (Oct 8, 2023):

It seems to be required 8GB at least for each model.
https://ollama.ai/library/llama2

So, my env is not good for it.

<!-- gh-comment-id:1751949743 --> @tacsotai commented on GitHub (Oct 8, 2023): It seems to be required 8GB at least for each model. https://ollama.ai/library/llama2 So, my env is not good for it.
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#62380
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?