mirror of
https://github.com/ollama/ollama.git
synced 2026-05-06 16:11:34 -05:00
Open
opened 2026-04-29 04:36:21 -05:00 by GiteaMirror
·
29 comments
No Branch/Tag Specified
main
dhiltgen/ci
parth-launch-plan-gating
hoyyeva/anthropic-reference-images-path
parth-anthropic-reference-images-path
brucemacd/download-before-remove
hoyyeva/editor-config-repair
parth-mlx-decode-checkpoints
parth-launch-codex-app
hoyyeva/fix-codex-model-metadata-warning
hoyyeva/qwen
parth/hide-claude-desktop-till-release
hoyyeva/opencode-image-modality
parth-add-claude-code-autoinstall
release_v0.22.0
pdevine/manifest-list
codex/fix-codex-model-metadata-warning
pdevine/addressable-manifest
brucemacd/launch-fetch-reccomended
jmorganca/llama-compat
launch-copilot-cli
hoyyeva/opencode-thinking
release_v0.20.7
parth-auto-save-backup
parth-test
jmorganca/gemma4-audio-replacements
fix-manifest-digest-on-pull
hoyyeva/vscode-improve
brucemacd/install-server-wait
parth/update-claude-docs
brucemac/start-ap-install
pdevine/mlx-update
pdevine/qwen35_vision
drifkin/api-show-fallback
mintlify/image-generation-1773352582
hoyyeva/server-context-length-local-config
jmorganca/faster-reptition-penalties
jmorganca/convert-nemotron
parth-pi-thinking
pdevine/sampling-penalties
jmorganca/fix-create-quantization-memory
dongchen/resumable_transfer_fix
pdevine/sampling-cache-error
jessegross/mlx-usage
hoyyeva/openclaw-config
hoyyeva/app-html
pdevine/qwen3next
brucemacd/sign-sh-install
brucemacd/tui-update
brucemacd/usage-api
jmorganca/launch-empty
fix-app-dist-embed
mxyng/mlx-compile
mxyng/mlx-quant
mxyng/mlx-glm4.7
mxyng/mlx
brucemacd/simplify-model-picker
jmorganca/qwen3-concurrent
fix-glm-4.7-flash-mla-config
drifkin/qwen3-coder-opening-tag
brucemacd/usage-cli
fix-cuda12-fattn-shmem
ollama-imagegen-docs
parth/fix-multiline-inputs
brucemacd/config-docs
mxyng/model-files
mxyng/simple-execute
fix-imagegen-ollama-models
mxyng/async-upload
jmorganca/lazy-no-dtype-changes
imagegen-auto-detect-create
parth/decrease-concurrent-download-hf
fix-mlx-quantize-init
jmorganca/x-cleanup
usage
imagegen-readme
jmorganca/glm-image
mlx-gpu-cd
jmorganca/imagegen-modelfile
parth/agent-skills
parth/agent-allowlist
parth/signed-in-offline
parth/agents
parth/fix-context-chopping
improve-cloud-flow
parth/add-models-websearch
parth/prompt-renderer-mcp
jmorganca/native-settings
jmorganca/download-stream-hash
jmorganca/client2-rebased
brucemacd/oai-chat-req-multipart
jessegross/multi_chunk_reserve
grace/additional-omit-empty
grace/mistral-3-large
mxyng/tokenizer2
mxyng/tokenizer
jessegross/flash
hoyyeva/windows-nacked-app
mxyng/cleanup-attention
grace/deepseek-parser
hoyyeva/remember-unsent-prompt
parth/add-lfs-pointer-error-conversion
parth/olmo2-test2
hoyyeva/ollama-launchagent-plist
nicole/olmo-model
parth/olmo-test
mxyng/remove-embedded
parth/render-template
jmorganca/intellect-3
parth/remove-prealloc-linter
jmorganca/cmd-eval
nicole/nomic-embed-text-fix
mxyng/lint-2
hoyyeva/add-gemini-3-pro-preview
hoyyeva/load-model-list
mxyng/expand-path
mxyng/environ-2
hoyyeva/deeplink-json-encoding
parth/improve-tool-calling-tests
hoyyeva/conversation
hoyyeva/assistant-edit-response
hoyyeva/thinking
origin/brucemacd/invalid-char-i-err
parth/improve-tool-calling
jmorganca/required-omitempty
grace/qwen3-vl-tests
mxyng/iter-client
parth/docs-readme
nicole/embed-test
pdevine/integration-benchstat
parth/remove-generate-cmd
parth/add-toolcall-id
mxyng/server-tests
jmorganca/glm-4.6
jmorganca/gin-h-compat
drifkin/stable-tool-args
pdevine/qwen3-more-thinking
parth/add-websearch-client
nicole/websearch_local
jmorganca/qwen3-coder-updates
grace/deepseek-v3-migration-tests
mxyng/fix-create
jmorganca/cloud-errors
pdevine/parser-tidy
revert-12233-parth/simplify-entrypoints-runner
parth/enable-so-gpt-oss
brucemacd/qwen3vl
jmorganca/readme-simplify
parth/gpt-oss-structured-outputs
revert-12039-jmorganca/tools-braces
mxyng/embeddings
mxyng/gguf
mxyng/benchmark
mxyng/types-null
parth/move-parsing
mxyng/gemma2
jmorganca/docs
mxyng/16-bit
mxyng/create-stdin
pdevine/authorizedkeys
mxyng/quant
parth/opt-in-error-context-window
brucemacd/cache-models
brucemacd/runner-completion
jmorganca/llama-update-6
brucemacd/benchmark-list
brucemacd/partial-read-caps
parth/deepseek-r1-tools
mxyng/omit-array
parth/tool-prefix-temp
brucemacd/runner-test
jmorganca/qwen25vl
brucemacd/model-forward-test-ext
parth/python-function-parsing
jmorganca/cuda-compression-none
drifkin/num-parallel
drifkin/chat-truncation-fix
jmorganca/sync
parth/python-tools-calling
drifkin/array-head-count
brucemacd/create-no-loop
parth/server-enable-content-stream-with-tools
qwen25omni
mxyng/v3
brucemacd/ropeconfig
jmorganca/silence-tokenizer
parth/sample-so-test
parth/sampling-structured-outputs
brucemacd/doc-go-engine
parth/constrained-sampling-json
jmorganca/mistral-wip
brucemacd/mistral-small-convert
parth/sample-unmarshal-json-for-params
brucemacd/jomorganca/mistral
pdevine/bfloat16
jmorganca/mistral
brucemacd/mistral
pdevine/logging
parth/sample-correctness-fix
parth/sample-fix-sorting
jmorgan/sample-fix-sorting-extras
jmorganca/temp-0-images
brucemacd/parallel-embed-models
brucemacd/shim-grammar
jmorganca/fix-gguf-error
bmizerany/nameswork
jmorganca/faster-releases
bmizerany/validatenames
brucemacd/err-no-vocab
brucemacd/rope-config
brucemacd/err-hint
brucemacd/qwen2_5
brucemacd/logprobs
brucemacd/new_runner_graph_bench
progress-flicker
brucemacd/forward-test
brucemacd/go_qwen2
pdevine/gemma2
jmorganca/add-missing-symlink-eval
mxyng/next-debug
parth/set-context-size-openai
brucemacd/next-bpe-bench
brucemacd/next-bpe-test
brucemacd/new_runner_e2e
brucemacd/new_runner_qwen2
pdevine/convert-cohere2
brucemacd/convert-cli
parth/log-probs
mxyng/next-mlx
mxyng/cmd-history
parth/templating
parth/tokenize-detokenize
brucemacd/check-key-register
bmizerany/grammar
jmorganca/vendor-081b29bd
mxyng/func-checks
jmorganca/fix-null-format
parth/fix-default-to-warn-json
jmorganca/qwen2vl
jmorganca/no-concat
parth/cmd-cleanup-SO
brucemacd/check-key-register-structured-err
parth/openai-stream-usage
parth/fix-referencing-so
stream-tools-stop
jmorganca/degin-1
brucemacd/install-path-clean
brucemacd/push-name-validation
brucemacd/browser-key-register
jmorganca/openai-fix-first-message
jmorganca/fix-proxy
jessegross/sample
parth/disallow-streaming-tools
dhiltgen/remove_submodule
jmorganca/ga
jmorganca/mllama
pdevine/newlines
pdevine/geems-2b
jmorganca/llama-bump
mxyng/modelname-7
mxyng/gin-slog
mxyng/modelname-6
jyan/convert-prog
jyan/quant5
paligemma-support
pdevine/import-docs
jmorganca/openai-context
jyan/paligemma
jyan/p2
jyan/palitest
bmizerany/embedspeedup
jmorganca/llama-vit
brucemacd/allow-ollama
royh/ep-methods
royh/whisper
mxyng/api-models
mxyng/fix-memory
jyan/q4_4/8
jyan/ollama-v
royh/stream-tools
roy-embed-parallel
bmizerany/hrm
revert-5963-revert-5924-mxyng/llama3.1-rope
royh/embed-viz
jyan/local2
jyan/auth
jyan/local
jyan/parse-temp
jmorganca/template-mistral
jyan/reord-g
royh-openai-suffixdocs
royh-imgembed
royh-embed-parallel
jyan/quant4
royh-precision
jyan/progress
pdevine/fix-template
jyan/quant3
pdevine/ggla
mxyng/update-registry-domain
jmorganca/ggml-static
mxyng/create-context
jyan/v0.146
mxyng/layers-from-files
build_dist
bmizerany/noseek
royh-ls
royh-name
timeout
mxyng/server-timestamp
bmizerany/nosillyggufslurps
royh-params
jmorganca/llama-cpp-7c26775
royh-openai-delete
royh-show-rigid
jmorganca/enable-fa
jmorganca/no-error-template
jyan/format
royh-testdelete
bmizerany/fastverify
language_support
pdevine/ps-glitches
brucemacd/tokenize
bruce/iq-quants
bmizerany/filepathwithcoloninhost
mxyng/split-bin
bmizerany/client-registry
jmorganca/if-none-match
native
jmorganca/native
jmorganca/batch-embeddings
jmorganca/initcmake
jmorganca/mm
pdevine/showggmlinfo
modenameenforcealphanum
bmizerany/modenameenforcealphanum
jmorganca/done-reason
jmorganca/llama-cpp-8960fe8
ollama.com
bmizerany/filepathnobuild
bmizerany/types/model/defaultfix
rmdisplaylong
nogogen
bmizerany/x
modelfile-readme
bmizerany/replacecolon
jmorganca/limit
jmorganca/execstack
jmorganca/replace-assets
mxyng/tune-concurrency
jmorganca/testing
whitespace-detection
jmorganca/options
upgrade-all
scratch
cuda-search
mattw/airenamer
mattw/allmodelsonhuggingface
mattw/quantcontext
mattw/whatneedstorun
brucemacd/llama-mem-calc
mattw/faq-context
mattw/communitylinks
mattw/noprune
mattw/python-functioncalling
rename
mxyng/install
pulse
remove-first
editor
mattw/selfqueryingretrieval
cgo
mattw/howtoquant
api
matt/streamingapi
format-config
mxyng/extra-args
shell
update-nous-hermes
cp-model
upload-progress
fix-unknown-model
fix-model-names
delete-fix
insecure-registry
ls
deletemodels
progressbar
readme-updates
license-layers
skip-list
list-models
modelpath
matt/examplemodelfiles
distribution
go-opts
v0.23.1
v0.23.1-rc0
v0.23.0
v0.23.0-rc0
v0.22.1
v0.22.1-rc1
v0.22.1-rc0
v0.22.0
v0.22.0-rc1
v0.21.3-rc0
v0.21.2-rc1
v0.21.2
v0.21.2-rc0
v0.21.1
v0.21.1-rc1
v0.21.1-rc0
v0.21.0
v0.21.0-rc1
v0.21.0-rc0
v0.20.8-rc0
v0.20.7
v0.20.7-rc1
v0.20.7-rc0
v0.20.6
v0.20.6-rc1
v0.20.6-rc0
v0.20.5
v0.20.5-rc2
v0.20.5-rc1
v0.20.5-rc0
v0.20.4
v0.20.4-rc2
v0.20.4-rc1
v0.20.4-rc0
v0.20.3
v0.20.3-rc0
v0.20.2
v0.20.1
v0.20.1-rc2
v0.20.1-rc1
v0.20.1-rc0
v0.20.0
v0.20.0-rc1
v0.20.0-rc0
v0.19.0
v0.19.0-rc2
v0.19.0-rc1
v0.19.0-rc0
v0.18.4-rc1
v0.18.4-rc0
v0.18.3
v0.18.3-rc2
v0.18.3-rc1
v0.18.3-rc0
v0.18.2
v0.18.2-rc1
v0.18.2-rc0
v0.18.1
v0.18.1-rc1
v0.18.1-rc0
v0.18.0
v0.18.0-rc2
v0.18.0-rc1
v0.18.0-rc0
v0.17.8-rc4
v0.17.8-rc3
v0.17.8-rc2
v0.17.8-rc1
v0.17.8-rc0
v0.17.7
v0.17.7-rc2
v0.17.7-rc1
v0.17.7-rc0
v0.17.6
v0.17.5
v0.17.4
v0.17.3
v0.17.2
v0.17.1
v0.17.1-rc2
v0.17.1-rc1
v0.17.1-rc0
v0.17.0
v0.17.0-rc2
v0.17.0-rc1
v0.17.0-rc0
v0.16.3
v0.16.3-rc2
v0.16.3-rc1
v0.16.3-rc0
v0.16.2
v0.16.2-rc0
v0.16.1
v0.16.0
v0.16.0-rc2
v0.16.0-rc0
v0.16.0-rc1
v0.15.6
v0.15.5
v0.15.5-rc5
v0.15.5-rc4
v0.15.5-rc3
v0.15.5-rc2
v0.15.5-rc1
v0.15.5-rc0
v0.15.4
v0.15.3
v0.15.2
v0.15.1
v0.15.1-rc1
v0.15.1-rc0
v0.15.0-rc6
v0.15.0
v0.15.0-rc5
v0.15.0-rc4
v0.15.0-rc3
v0.15.0-rc2
v0.15.0-rc1
v0.15.0-rc0
v0.14.3
v0.14.3-rc3
v0.14.3-rc2
v0.14.3-rc1
v0.14.3-rc0
v0.14.2
v0.14.2-rc1
v0.14.2-rc0
v0.14.1
v0.14.0-rc11
v0.14.0
v0.14.0-rc10
v0.14.0-rc9
v0.14.0-rc8
v0.14.0-rc7
v0.14.0-rc6
v0.14.0-rc5
v0.14.0-rc4
v0.14.0-rc3
v0.14.0-rc2
v0.14.0-rc1
v0.14.0-rc0
v0.13.5
v0.13.5-rc1
v0.13.5-rc0
v0.13.4-rc2
v0.13.4
v0.13.4-rc1
v0.13.4-rc0
v0.13.3
v0.13.3-rc1
v0.13.3-rc0
v0.13.2
v0.13.2-rc2
v0.13.2-rc1
v0.13.2-rc0
v0.13.1
v0.13.1-rc2
v0.13.1-rc1
v0.13.1-rc0
v0.13.0
v0.13.0-rc0
v0.12.11
v0.12.11-rc1
v0.12.11-rc0
v0.12.10
v0.12.10-rc1
v0.12.10-rc0
v0.12.9-rc0
v0.12.9
v0.12.8
v0.12.8-rc0
v0.12.7
v0.12.7-rc1
v0.12.7-rc0
v0.12.7-citest0
v0.12.6
v0.12.6-rc1
v0.12.6-rc0
v0.12.5
v0.12.5-rc0
v0.12.4
v0.12.4-rc7
v0.12.4-rc6
v0.12.4-rc5
v0.12.4-rc4
v0.12.4-rc3
v0.12.4-rc2
v0.12.4-rc1
v0.12.4-rc0
v0.12.3
v0.12.2
v0.12.2-rc0
v0.12.1
v0.12.1-rc1
v0.12.1-rc2
v0.12.1-rc0
v0.12.0
v0.12.0-rc1
v0.12.0-rc0
v0.11.11
v0.11.11-rc3
v0.11.11-rc2
v0.11.11-rc1
v0.11.11-rc0
v0.11.10
v0.11.9
v0.11.9-rc0
v0.11.8
v0.11.8-rc0
v0.11.7-rc1
v0.11.7-rc0
v0.11.7
v0.11.6
v0.11.6-rc0
v0.11.5-rc4
v0.11.5-rc3
v0.11.5
v0.11.5-rc5
v0.11.5-rc2
v0.11.5-rc1
v0.11.5-rc0
v0.11.4
v0.11.4-rc0
v0.11.3
v0.11.3-rc0
v0.11.2
v0.11.1
v0.11.0-rc0
v0.11.0-rc1
v0.11.0-rc2
v0.11.0
v0.10.2-int1
v0.10.1
v0.10.0
v0.10.0-rc4
v0.10.0-rc3
v0.10.0-rc2
v0.10.0-rc1
v0.10.0-rc0
v0.9.7-rc1
v0.9.7-rc0
v0.9.6
v0.9.6-rc0
v0.9.6-ci0
v0.9.5
v0.9.4-rc5
v0.9.4-rc6
v0.9.4
v0.9.4-rc3
v0.9.4-rc4
v0.9.4-rc1
v0.9.4-rc2
v0.9.4-rc0
v0.9.3
v0.9.3-rc5
v0.9.4-citest0
v0.9.3-rc4
v0.9.3-rc3
v0.9.3-rc2
v0.9.3-rc1
v0.9.3-rc0
v0.9.2
v0.9.1
v0.9.1-rc1
v0.9.1-rc0
v0.9.1-ci1
v0.9.1-ci0
v0.9.0
v0.9.0-rc0
v0.8.0
v0.8.0-rc0
v0.7.1-rc2
v0.7.1
v0.7.1-rc1
v0.7.1-rc0
v0.7.0
v0.7.0-rc1
v0.7.0-rc0
v0.6.9-rc0
v0.6.8
v0.6.8-rc0
v0.6.7
v0.6.7-rc2
v0.6.7-rc1
v0.6.7-rc0
v0.6.6
v0.6.6-rc2
v0.6.6-rc1
v0.6.6-rc0
v0.6.5-rc1
v0.6.5
v0.6.5-rc0
v0.6.4-rc0
v0.6.4
v0.6.3-rc1
v0.6.3
v0.6.3-rc0
v0.6.2
v0.6.2-rc0
v0.6.1
v0.6.1-rc0
v0.6.0-rc0
v0.6.0
v0.5.14-rc0
v0.5.13
v0.5.13-rc6
v0.5.13-rc5
v0.5.13-rc4
v0.5.13-rc3
v0.5.13-rc2
v0.5.13-rc1
v0.5.13-rc0
v0.5.12
v0.5.12-rc1
v0.5.12-rc0
v0.5.11
v0.5.10
v0.5.9
v0.5.9-rc0
v0.5.8-rc13
v0.5.8
v0.5.8-rc12
v0.5.8-rc11
v0.5.8-rc10
v0.5.8-rc9
v0.5.8-rc8
v0.5.8-rc7
v0.5.8-rc6
v0.5.8-rc5
v0.5.8-rc4
v0.5.8-rc3
v0.5.8-rc2
v0.5.8-rc1
v0.5.8-rc0
v0.5.7
v0.5.6
v0.5.5
v0.5.5-rc0
v0.5.4
v0.5.3
v0.5.3-rc0
v0.5.2
v0.5.2-rc3
v0.5.2-rc2
v0.5.2-rc1
v0.5.2-rc0
v0.5.1
v0.5.0
v0.5.0-rc1
v0.4.8-rc0
v0.4.7
v0.4.6
v0.4.5
v0.4.4
v0.4.3
v0.4.3-rc0
v0.4.2
v0.4.2-rc1
v0.4.2-rc0
v0.4.1
v0.4.1-rc0
v0.4.0
v0.4.0-rc8
v0.4.0-rc7
v0.4.0-rc6
v0.4.0-rc5
v0.4.0-rc4
v0.4.0-rc3
v0.4.0-rc2
v0.4.0-rc1
v0.4.0-rc0
v0.4.0-ci3
v0.3.14
v0.3.14-rc0
v0.3.13
v0.3.12
v0.3.12-rc5
v0.3.12-rc4
v0.3.12-rc3
v0.3.12-rc2
v0.3.12-rc1
v0.3.11
v0.3.11-rc4
v0.3.11-rc3
v0.3.11-rc2
v0.3.11-rc1
v0.3.10
v0.3.10-rc1
v0.3.9
v0.3.8
v0.3.7
v0.3.7-rc6
v0.3.7-rc5
v0.3.7-rc4
v0.3.7-rc3
v0.3.7-rc2
v0.3.7-rc1
v0.3.6
v0.3.5
v0.3.4
v0.3.3
v0.3.2
v0.3.1
v0.3.0
v0.2.8
v0.2.8-rc2
v0.2.8-rc1
v0.2.7
v0.2.6
v0.2.5
v0.2.4
v0.2.3
v0.2.2
v0.2.2-rc2
v0.2.2-rc1
v0.2.1
v0.2.0
v0.1.49-rc14
v0.1.49-rc13
v0.1.49-rc12
v0.1.49-rc11
v0.1.49-rc10
v0.1.49-rc9
v0.1.49-rc8
v0.1.49-rc7
v0.1.49-rc6
v0.1.49-rc4
v0.1.49-rc5
v0.1.49-rc3
v0.1.49-rc2
v0.1.49-rc1
v0.1.48
v0.1.47
v0.1.46
v0.1.45-rc5
v0.1.45
v0.1.45-rc4
v0.1.45-rc3
v0.1.45-rc2
v0.1.45-rc1
v0.1.44
v0.1.43
v0.1.42
v0.1.41
v0.1.40
v0.1.40-rc1
v0.1.39
v0.1.39-rc2
v0.1.39-rc1
v0.1.38
v0.1.37
v0.1.36
v0.1.35
v0.1.35-rc1
v0.1.34
v0.1.34-rc1
v0.1.33
v0.1.33-rc7
v0.1.33-rc6
v0.1.33-rc5
v0.1.33-rc4
v0.1.33-rc3
v0.1.33-rc2
v0.1.33-rc1
v0.1.32
v0.1.32-rc2
v0.1.32-rc1
v0.1.31
v0.1.30
v0.1.29
v0.1.28
v0.1.27
v0.1.26
v0.1.25
v0.1.24
v0.1.23
v0.1.22
v0.1.21
v0.1.20
v0.1.19
v0.1.18
v0.1.17
v0.1.16
v0.1.15
v0.1.14
v0.1.13
v0.1.12
v0.1.11
v0.1.10
v0.1.9
v0.1.8
v0.1.7
v0.1.6
v0.1.5
v0.1.4
v0.1.3
v0.1.2
v0.1.1
v0.1.0
v0.0.21
v0.0.20
v0.0.19
v0.0.18
v0.0.17
v0.0.16
v0.0.15
v0.0.14
v0.0.13
v0.0.12
v0.0.11
v0.0.10
v0.0.9
v0.0.8
v0.0.7
v0.0.6
v0.0.5
v0.0.4
v0.0.3
v0.0.2
v0.0.1
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
python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
Mirrored from GitHub Pull Request
Milestone
No items
No Milestone
Projects
Clear projects
No project
No Assignees
Notifications
Due Date
No due date set.
Dependencies
No dependencies set.
Reference: github-starred/ollama#53730
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
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?
Originally created by @TobiasG0 on GitHub (Jun 3, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10956
What is the issue?
Description
I'm encountering an issue when using the
llama3.2-vision:11bmodel via Ollama Docker to generate image descriptions.Problem
Configuration
num_ctx: 32768num_predict: 4096The prompt includes:
Notes
llama3.2-vision:11bmodel.Relevant log output
OS
Docker
GPU
Nvidia
CPU
Intel
Ollama version
0.9.0
@rick-github commented on GitHub (Jun 3, 2025):
If you set
OLLAMA_DEBUG=1there will be some additional information logged that might be useful. How do you get the model back to a properly functioning state?@TobiasG0 commented on GitHub (Jun 3, 2025):
I can get the model back into a functioning state by restarting the Ollama Docker container. After that, the first request works, but all subsequent requests produce garbage output until the Docker container is restarted again.
Ollama log using
OLLAMA_DEBUG=1:detailed_ollama_log.txt
@rick-github commented on GitHub (Jun 3, 2025):
Try stopping the model rather than restarting the container, that may disambiguate between a server problem or a runner problem.
docker exec <name-of-container> ollama stop llama3.2-vision:11bor set"keep_alive":0in the API call. Also try running the model without GPU by setting"options":{"num_gpu":0}in the API call. It will run slower and will probably run multiple inferences without a problem, but worth checking.@TobiasG0 commented on GitHub (Jun 3, 2025):
I'm observing the same behavior when stopping the model between runs. The first request after startup works correctly, but after stopping the model and sending a second request with the same input, the response is garbage.
I've attached the logs for this scenario:
ollama_stop_logs.txt
The same issue occurs when running the model exclusively on the CPU:
ollama_cpu_logs.txt
I've also included two sample responses from the model using the same input:
The first response was generated after restarting the container:
ollama_cpu_response_good.txt
The second response was generated directly after the first one with the same input, without restarting the container:
ollama_cpu_response_bad.txt
@rick-github commented on GitHub (Jun 3, 2025):
That's interesting - it's independent of the runner and GPU implying a server fault. I raised it as a possible issue, but in my experience it's never the server. How did you install ollama?
@TobiasG0 commented on GitHub (Jun 3, 2025):
I use the official Ollama Docker image: https://hub.docker.com/r/ollama/ollama
More specifically, I use the following Docker Compose file:
docker-compose.txt
@SugarcaneDefender commented on GitHub (Jun 19, 2025):
I will also add that I get this issue, also when using the Ollama API on a Windows install. I have this issue with Llava Phi-3. @TobiasG0 , when you send the image, what does your prompt look like? Mine contains text and words, and some of the words are in additional appended messages in the history.
Perhaps there is an issue with the image pipeline with the API when sending multiple messages?
@SugarcaneDefender commented on GitHub (Jun 19, 2025):
Update - lowering the ammount of context I am sending fixed the issue, I would try raw dogging a message with no context from the API. My issue is solved (although it still not good that it isn't able to auto-shorten context as needed). For future reference of anyone reading this, I also got a lot of "You" and "Your" generated when mine LLM was making garbage. Hope this helps someone!
@TobiasG0 commented on GitHub (Jun 19, 2025):
I'm sending a single user message that includes both the image and the prompt. The prompt usually contains instructions along with additional information about the image. That's also why I’ve set my context window to 32k - some prompts can be quite long due to the additional information.
I could also reduce my context, but then some of the information about the image would be missing. The model should normally be able to handle such large contexts.
@TobiasG0 commented on GitHub (Jun 19, 2025):
@rick-github, are there any updates from your side?
@PDeveloper commented on GitHub (Jun 30, 2025):
I am getting the same behaviour after updating - any llama3.2-vision request will output the json response, followed by extremely random tokens. This wasn't there before updating (and I haven't in a long time).
Now I'm considering reverting otherwise my project is cooked.
Instead of using the Pydantic Model JsonSchemaValue for the format, if I simply use 'json' as a string for the format, it works correctly...
@tgreenhaw5 commented on GitHub (Jun 30, 2025):
I also have this issue with exactly the same symptoms. Loaded on windows 11 and it does this both by CLI and API. Ran a clean install and even tried running an old installer that used to work fine.
@PDeveloper commented on GitHub (Jul 1, 2025):
Working the problem over the last day, I have managed to get some improvement by modifying the raw json schema Pydantic gives me:
As well as removing any Optional fields from the model. This gets me the old behaviour, only trouble now is it sometimes returns an incomplete response, so the json string randomly ends before finishing. For this I added a retry loop increasing the temperature as a workaround, but still highly unreliable... (I know these are LLMs, but before there was some semblance of consistency).
Hope this helps others.
Edit:
Even with this method, I'm still getting the garbage output once in a while, or incomplete JSONs:
@TobiasG0 commented on GitHub (Jul 6, 2025):
Update: The issue persists with Ollama version 0.9.5.
@tgreenhaw5 commented on GitHub (Jul 7, 2025):
I got better results when I set option no repeat to 1 to force no repetition, but it’s not working really well anymore. It’s likely that an undefined default variable or default settings changed without regression testing.
I switched to qwen2.5vl:7b and it’s working without issues and frankly better results.
@viulian commented on GitHub (Aug 15, 2025):
I (think I) encounter this identical problem while doing batch processing of images. ollama version is 0.11.4.
Without
num_predictollama seemed to "hang" somewhere between the 2nd and 5th image. Withnum_predictset, it doesn't hang, but responses start having gibberish. Restarting ollama produces correct output, but the same situation repeats.Adding a 5s sleep after each sequential call seems to help - it handles more calls before responses have gibberish - but, eventually, it ends up in the same scenario.
@raffaeler commented on GitHub (Sep 13, 2025):
I am also stuck with batch processing hanging after a few images. It works using other models like llava (which is definitely inferior for quality of the descriptions).
@tgreenhaw5 commented on GitHub (Sep 13, 2025):
Have you tried qwen2.5vl:7b? How does it compare for you?
@raffaeler commented on GitHub (Sep 14, 2025):
@tgreenhaw5 The model card on the Ollama library reports that
qwen2.5vlrequiresOllama 0.7.0.I am not sure if this means an older version or the current, newer version.
Did you try it with the current release? I certainly can't go back for other models.
@tgreenhaw5 commented on GitHub (Sep 14, 2025):
I'm was using 0.11.4 and it works fine. I noticed I was a behind few minor versions so I loaded that and OLLAMA -v reports 0.11.10 and it too works fine.
Maybe "requires Ollama 0.7.0" means minimum version?
@raffaeler commented on GitHub (Sep 14, 2025):
@tgreenhaw5 Yes
qwen2.5vlworks correctly. Anyway, the model generates much shorter descriptions compared tollama3.2-vision. For my use-case, a detailed description worked better.I hope the incompatibility between the current Ollama "newer" versions and the
llama3.2-visionmodel will be fixed soon.@rick-github commented on GitHub (Sep 14, 2025):
In general, qwen2.5vl works fine for any release from 0.7.0 onwards. Similarly, llama3.2-vision should work across all ollama versions since 0.4.0. The problem is, frustratingly, that there's a small set of users for which the model doesn't perform fine. I have been unable to replicate the problem on a variety of Nvidia and AMD hardware. If you are able to supply a script or procedure that reliably demonstrates the problem that would be very helpful. Failing that, a full log with
OLLAMA_DEBUG=1might provide some insight.@raffaeler commented on GitHub (Sep 14, 2025):
@rick-github I understand that, in fact in my Python code I can make a couple of requests and the description generation is successful. After that it simply hangs and I could not find no useful log to provide an explanation.
FYI I am on Ubuntu 24.04 with an RTX4060 with the headless drivers which makes the GPU only available to apps (in this case the script using Ollama).
I'll do more research, but it can take some time as I am preparing a talk and I can currently rely on the descriptions (several hundreds) I generated (with
llama3.2-vision) before upgrading Ollama.@tgreenhaw5 commented on GitHub (Sep 14, 2025):
@tgreenhaw5 commented on GitHub (Sep 14, 2025):
Interesting... I was going to provide as much detail as possible to replicate the issue, but I can no longer get it to fail. llamma3.2-vision failed almost immediately every time for me but it has been a while since I tried. I updated from 0.11.4 to 0.11.10 today and perhaps something has changed that corrects the problem.
I use Windows 11 on a 3090.
If I can get it to fail again, I will provide as much detail as possible.
@raffaeler commented on GitHub (Sep 14, 2025):
I'm also on
0.11.10but on Ubuntu, and it always fails after very few images.@0x6r1an0y commented on GitHub (Sep 21, 2025):
Environment:
0.12.0Windows 11NVIDIA RTX 3090 (driver 576.80, CUDA 12.9)Still get gibberish on
llama3.2-vision. Switched toqwen2.5-vland got better results.@x86Gr commented on GitHub (Oct 4, 2025):
ollama 12.3
Debian 13.1
bare metal installation, no docker.
I can confirm that llama3.2 vision worked wonders up until about version 0.8.0 or earlier, with 12.3 it's simply unusable, tried on the same dataset and the results went from 11b rivalling gemma3-27b Q4_K_M to being garbage.
@rick-github commented on GitHub (Oct 4, 2025):
If you are able to supply a script or procedure that reliably demonstrates the problem that would be very helpful. Failing that, a full log with OLLAMA_DEBUG=1 might provide some insight.