llm, make the ollama_usage output much fancier, more report-like.
This commit is contained in:
me committed
1 parent
797744d9fe
commit
8311427506
1 file changed
+156
-13
@@ -178,6 +178,120 @@
|
||||
#- deepseek-r1:1.5b
|
||||
#- deepseek-r1:7b
|
||||
|
||||
### 2026-10-18, checking the actual RAM usage of the models... ###
|
||||
|
||||
# `ollama_sizes m 16000`
|
||||
#| Model Name | HDD (ls) | Context | RAM (ps) |
|
||||
#| :------------------------ | -----------: | -------: | -----------: |
|
||||
#| mistral-nemo:12b | 7.1GB | 16000 | 10GB |
|
||||
#| ministral-3:14b | 9.1GB | 16000 | 11GB |
|
||||
#| ministral-3:8b | 6.0GB | 16000 | 7.8GB |
|
||||
#| ministral-3:3b | 3.0GB | 16000 | 4.1GB |
|
||||
#| mistral-small3.2:24b | 15GB | 16000 | 17GB |
|
||||
#| mistral:7b | 4.4GB | 16000 | 6.8GB |
|
||||
#| codestral:22b | 12GB | 16000 | 16GB |
|
||||
#| devstral-small-2:24b | 15GB | 16000 | 17GB |
|
||||
#| qwen2.5-coder:32b | 19GB | 16000 | 24GB |
|
||||
#| qwen2.5-coder:14b | 9.0GB | 16000 | 12GB |
|
||||
#| qwen2.5-coder:7b | 4.7GB | 16000 | 5.9GB |
|
||||
#| qwen2.5-coder:3b | 1.9GB | 16000 | 2.7GB |
|
||||
#| qwen2.5-coder:1.5b | 986MB | 16000 | 1.6GB |
|
||||
#| qwen2.5-coder:0.5b | 397MB | 16000 | 701MB |
|
||||
#| qwen3-coder:30b | 18GB | 16000 | 20GB |
|
||||
#| qwen3.5:35b | 22GB | 16000 | 22GB |
|
||||
#| qwen3.5:27b | 17GB | 16000 | 18GB |
|
||||
#| qwen3.5:9b | 6.6GB | 16000 | 6.7GB |
|
||||
#| qwen3.5:4b | 3.3GB | 16000 | 3.7GB |
|
||||
#| qwen3.5:2b | 2.7GB | 16000 | 2.6GB |
|
||||
#| qwen3.5:0.8b | 1.3GB | 16000 | 630MB |
|
||||
#| qwen3.6:35b | 22GB | 16000 | 22GB |
|
||||
#| qwen3.6:27b | 17GB | 16000 | 18GB |
|
||||
#| qwen3.8:27b | 17GB | 16000 | 18GB |
|
||||
|
||||
# `ollama_sizes m 32000`
|
||||
#| Model Name | HDD (ls) | Context | RAM (ps) |
|
||||
#| :------------------------ | -----------: | -------: | -----------: |
|
||||
#| mistral-nemo:12b | 7.1GB | 32000 | 12GB |
|
||||
#| ministral-3:14b | 9.1GB | 32000 | 13GB |
|
||||
#| ministral-3:8b | 6.0GB | 32000 | 10GB |
|
||||
#| ministral-3:3b | 3.0GB | 32000 | 5.9GB |
|
||||
#| mistral-small3.2:24b | 15GB | 32000 | 20GB |
|
||||
#| mistral:7b | 4.4GB | 32000 | 8.9GB |
|
||||
#| codestral:22b | 12GB | 32000 | 20GB |
|
||||
#| devstral-small-2:24b | 15GB | 32000 | 20GB |
|
||||
#| qwen2.5-coder:32b | 19GB | 32000 | 28GB |
|
||||
#| qwen2.5-coder:14b | 9.0GB | 32000 | 15GB |
|
||||
#| qwen2.5-coder:7b | 4.7GB | 32000 | 6.9GB |
|
||||
#| qwen2.5-coder:3b | 1.9GB | 32000 | 3.3GB |
|
||||
#| qwen2.5-coder:1.5b | 986MB | 32000 | 2.1GB |
|
||||
#| qwen2.5-coder:0.5b | 397MB | 32000 | 929MB |
|
||||
#| qwen3-coder:30b | 18GB | 32000 | 21GB |
|
||||
#| qwen3.5:35b | 22GB | 32000 | 22GB |
|
||||
#| qwen3.5:27b | 17GB | 32000 | 19GB |
|
||||
#| qwen3.5:9b | 6.6GB | 32000 | 7.3GB |
|
||||
#| qwen3.5:4b | 3.3GB | 32000 | 4.2GB |
|
||||
#| qwen3.5:2b | 2.7GB | 32000 | 2.8GB |
|
||||
#| qwen3.5:0.8b | 1.3GB | 32000 | 695MB |
|
||||
#| qwen3.6:35b | 22GB | 32000 | 22GB |
|
||||
#| qwen3.6:27b | 17GB | 32000 | 18GB |
|
||||
#| qwen3.8:27b | 17GB | 32000 | 18GB |
|
||||
|
||||
# `ollama_sizes m 64000`
|
||||
#| Model Name | HDD (ls) | Context | RAM (ps) |
|
||||
#| :------------------------ | -----------: | -------: | -----------: |
|
||||
#| mistral-nemo:12b | 7.1GB | 64000 | 18GB |
|
||||
#| ministral-3:14b | 9.1GB | 64000 | 19GB |
|
||||
#| ministral-3:8b | 6.0GB | 64000 | 14GB |
|
||||
#| ministral-3:3b | 3.0GB | 64000 | 9.6GB |
|
||||
#| mistral-small3.2:24b | 15GB | 64000 | 26GB |
|
||||
#| mistral:7b | 4.4GB | 32768 | 9.0GB |
|
||||
#| codestral:22b | 12GB | 32768 | 20GB |
|
||||
#| devstral-small-2:24b | 15GB | 64000 | 26GB |
|
||||
#| qwen2.5-coder:32b | 19GB | 32768 | 28GB |
|
||||
#| qwen2.5-coder:14b | 9.0GB | 32768 | 15GB |
|
||||
#| qwen2.5-coder:7b | 4.7GB | 32768 | 6.9GB |
|
||||
#| qwen2.5-coder:3b | 1.9GB | 32768 | 3.4GB |
|
||||
#| qwen2.5-coder:1.5b | 986MB | 32768 | 2.1GB |
|
||||
#| qwen2.5-coder:0.5b | 397MB | 32768 | 940MB |
|
||||
#| qwen3-coder:30b | 18GB | 64000 | 25GB |
|
||||
#| qwen3.5:35b | 22GB | 64000 | 23GB |
|
||||
#| qwen3.5:27b | 17GB | 64000 | 22GB |
|
||||
#| qwen3.5:9b | 6.6GB | 64000 | 8.8GB |
|
||||
#| qwen3.5:4b | 3.3GB | 64000 | 5.6GB |
|
||||
#| qwen3.5:2b | 2.7GB | 64000 | 3.5GB |
|
||||
#| qwen3.5:0.8b | 1.3GB | 64000 | 999MB |
|
||||
#| qwen3.6:35b | 22GB | 64000 | 22GB |
|
||||
#| qwen3.6:27b | 17GB | 64000 | 18GB |
|
||||
#| qwen3.8:27b | 17GB | 64000 | 18GB |
|
||||
|
||||
# `ollama_sizes m 256000`
|
||||
#| Model Name | HDD (ls) | Context | RAM (ps) |
|
||||
#| :------------------------ | -----------: | -------: | -----------: |
|
||||
#| mistral-nemo:12b | 7.1GB | 256000 | 50GB |
|
||||
#| ministral-3:14b | 9.1GB | 256000 | 51GB |
|
||||
#| ministral-3:8b | 6.0GB | 256000 | 42GB |
|
||||
#| ministral-3:3b | 3.0GB | 256000 | 30GB |
|
||||
#| mistral-small3.2:24b | 15GB | 131072 | 37GB |
|
||||
#| mistral:7b | 4.4GB | 32768 | 9.0GB |
|
||||
#| codestral:22b | 12GB | 32768 | 20GB |
|
||||
#| devstral-small-2:24b | 15GB | 256000 | 58GB |
|
||||
#| qwen2.5-coder:32b | 19GB | 32768 | 28GB |
|
||||
#| qwen2.5-coder:14b | 9.0GB | 32768 | 15GB |
|
||||
#| qwen2.5-coder:7b | 4.7GB | 32768 | 6.9GB |
|
||||
#| qwen2.5-coder:3b | 1.9GB | 32768 | 3.4GB |
|
||||
#| qwen2.5-coder:1.5b | 986MB | 32768 | 2.1GB |
|
||||
#| qwen2.5-coder:0.5b | 397MB | 32768 | 940MB |
|
||||
#| qwen3-coder:30b | 18GB | 256000 | 45GB |
|
||||
#| qwen3.5:35b | 22GB | 256000 | 28GB |
|
||||
#| qwen3.5:27b | 17GB | 256000 | 35GB |
|
||||
#| qwen3.5:9b | 6.6GB | 256000 | 15GB |
|
||||
#| qwen3.5:4b | 3.3GB | 256000 | 12GB |
|
||||
#| qwen3.5:2b | 2.7GB | 256000 | 6.7GB |
|
||||
#| qwen3.5:0.8b | 1.3GB | 256000 | 2.2GB |
|
||||
#| qwen3.6:35b | 22GB | 256000 | 23GB |
|
||||
#| qwen3.6:27b | 17GB | 256000 | 20GB |
|
||||
#| qwen3.8:27b | 17GB | 256000 | 20GB |
|
||||
|
||||
- name: Workstation | Linux | Software | LLMs | Facts | Merge | Print
|
||||
ansible.builtin.debug:
|
||||
var: "{{ item }}"
|
||||
@@ -841,34 +955,63 @@
|
||||
alias restart-models="restart_ai "
|
||||
|
||||
function ollama_sizes() {
|
||||
echo " Stopping all ollama usage..."
|
||||
sudo sv restart ollama
|
||||
# VAR1 - Format. Choices are Markdown or Spaces.
|
||||
typeset -l fmt="$1"
|
||||
if [[ -z "$fmt" ]]; then
|
||||
fmt=s
|
||||
fi
|
||||
if [[ "$fmt" != "s"* && "$fmt" != "m"* ]]; then
|
||||
echo "ERROR: Format incorrect, choose Markdown or Spaces."
|
||||
return 1
|
||||
fi
|
||||
sep=""
|
||||
if [[ $fmt == "m"* ]]; then
|
||||
sep="|"
|
||||
fi
|
||||
|
||||
# VAR2 - Context
|
||||
typeset -i num_ctx="$2"
|
||||
context=""
|
||||
if [[ -n $num_ctx ]]; then
|
||||
context=',"options":{"num_ctx":'$num_ctx'}'
|
||||
fi
|
||||
|
||||
# Column Formatting
|
||||
col1=25
|
||||
col2=12
|
||||
col3=8
|
||||
col4=12
|
||||
spacing="$sep %-${col1}s $sep %${col2}s $sep %${col3}s $sep %${col4}s $sep"
|
||||
|
||||
#echo " Stopping all ollama usage..."
|
||||
sudo sv restart ollama >/dev/null 2>&1
|
||||
|
||||
#echo -e "\n Checking model disk and RAM sizes...\n"
|
||||
|
||||
printf "$spacing\n" "Model Name" "HDD (ls)" "Context" "RAM (ps)"
|
||||
if [[ $fmt == "m"* ]]; then
|
||||
printf "$spacing\n" ":------------------------" "-----------:" "-------:" "-----------:"
|
||||
fi
|
||||
|
||||
echo -e "\n Checking model disk and RAM sizes...\n"
|
||||
echo "| Model Name | HDD (ls) | RAM (ps) |"
|
||||
echo "| +---- | --+ | --+ |"
|
||||
for model in `ollama ls | grep -v NAME | awk '{print $1}'`; do
|
||||
echo -n "| $model"
|
||||
#ollama run $model "" --format json >/dev/null 2>&1
|
||||
#set -x
|
||||
curl -s http://localhost:11434/api/generate \
|
||||
-d '{"model":"'$model'","prompt":"","stream":false,"keep_alive":1}' \
|
||||
-d '{"model":"'$model'","prompt":"","stream":false,"keep_alive":1'$context'}' \
|
||||
>/dev/null 2>&1
|
||||
set +x
|
||||
|
||||
hdd="`ollama ls | grep $model | awk '{print $3 $4}'`"
|
||||
echo -n " | $hdd"
|
||||
ram="`ollama ps | grep $model | awk '{print $3 $4}'`"
|
||||
echo -n " | $ram"
|
||||
ctx="`ollama ps | grep $model | awk '{print $7}'`"
|
||||
|
||||
printf "$spacing\n" "$model" "$hdd" "$ctx" "$ram"
|
||||
|
||||
ollama stop $model >/dev/null 2>&1
|
||||
while ollama ps | grep $model; do
|
||||
sleep 1
|
||||
done
|
||||
echo " |"
|
||||
done
|
||||
|
||||
echo "Done!!"
|
||||
#echo "Done!!"
|
||||
}
|
||||
alias ollama-sizes="ollama_sizes "
|
||||
alias model-sizes="ollama_sizes "
|
||||
|
||||
Reference in new issue
Block a user