matthias/local_ai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Adding more models

Browse Source
This commit is contained in:
Matthias Ladkau
2026-09-30 09:03:46 +02:00
parent 009a8f52a9
commit 3b0f82ecfa
2 changed files with 20 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
models.tsv
+8 -3
View File
@@ -3,10 +3,15 @@
# cpu_ok: yes = usable speed without a GPU (small dense or MoE with few active params). # cpu_ok: yes = usable speed without a GPU (small dense or MoE with few active params).
# rank: higher = better quality for coding; the recommender picks the highest rank that fits. # rank: higher = better quality for coding; the recommender picks the highest rank that fits.
qwen2.5-coder:1.5b 1.0 2.0 yes 10 Tiny; very fast, weak edits. For very small machines. qwen2.5-coder:1.5b 1.0 2.0 yes 10 Tiny; very fast, weak edits. For very small machines.
granite-code:3b 2.0 3.0 yes 15 IBM, Apache-2.0 (fully permissive); a bit weaker than Qwen at this size.
qwen2.5-coder:3b 1.9 3.0 yes 20 Small and fast; OK for simple edits. qwen2.5-coder:3b 1.9 3.0 yes 20 Small and fast; OK for simple edits.
granite-code:8b 4.6 6.2 yes 27 IBM, Apache-2.0 (fully permissive); solid mid-size coder.
qwen2.5-coder:7b 4.7 6.5 yes 30 Best all-round choice for laptops / CPU-only. qwen2.5-coder:7b 4.7 6.5 yes 30 Best all-round choice for laptops / CPU-only.
deepseek-coder-v2:16b 8.9 11.5 yes 35 MoE (2.4B active): fast on CPU, needs ~12 GB RAM. granite-code:20b 12 15 no 33 IBM, Apache-2.0 (fully permissive); dense, wants a GPU (~15 GB).
deepseek-coder-v2:16b 8.9 11.5 yes 35 MoE (Mixture of Experts, 2.4B active): fast on CPU, needs ~12 GB RAM.
qwen2.5-coder:14b 9.0 11.5 no 40 Noticeably smarter than 7B; wants a GPU (~12 GB VRAM). qwen2.5-coder:14b 9.0 11.5 no 40 Noticeably smarter than 7B; wants a GPU (~12 GB VRAM).
gpt-oss:20b 14 17 yes 50 MoE reasoning model; needs ~17 GB RAM or VRAM. gpt-oss:20b 14 17 yes 50 MoE (Mixture of Experts) reasoning model; needs ~17 GB RAM or VRAM.
qwen3-coder:30b 19 23 yes 60 MoE (3B active): strong coder, fast on CPU with 24+ GB RAM. granite-code:34b 19 23 no 55 IBM, Apache-2.0 (fully permissive); dense, needs a 24 GB GPU.
devstral:24b 14 17 no 58 Mistral+All Hands, Apache-2.0; built for agentic multi-file edits, needs ~17 GB RAM or VRAM.
qwen3-coder:30b 19 23 yes 60 MoE (Mixture of Experts, 3B active): strong coder, fast on CPU with 24+ GB RAM.
qwen2.5-coder:32b 20 24 no 70 Top-quality dense coder; needs a 24 GB GPU. qwen2.5-coder:32b 20 24 no 70 Top-quality dense coder; needs a 24 GB GPU.
1 # ollama_tag disk_gb mem_gb cpu_ok rank description
3 # cpu_ok: yes = usable speed without a GPU (small dense or MoE with few active params).
4 # rank: higher = better quality for coding; the recommender picks the highest rank that fits.
5 qwen2.5-coder:1.5b 1.0 2.0 yes 10 Tiny; very fast, weak edits. For very small machines.
6 granite-code:3b 2.0 3.0 yes 15 IBM, Apache-2.0 (fully permissive); a bit weaker than Qwen at this size.
7 qwen2.5-coder:3b 1.9 3.0 yes 20 Small and fast; OK for simple edits.
8 granite-code:8b 4.6 6.2 yes 27 IBM, Apache-2.0 (fully permissive); solid mid-size coder.
9 qwen2.5-coder:7b 4.7 6.5 yes 30 Best all-round choice for laptops / CPU-only.
10 deepseek-coder-v2:16b granite-code:20b 8.9 12 11.5 15 yes no 35 33 MoE (2.4B active): fast on CPU, needs ~12 GB RAM. IBM, Apache-2.0 (fully permissive); dense, wants a GPU (~15 GB).
11 deepseek-coder-v2:16b 8.9 11.5 yes 35 MoE (Mixture of Experts, 2.4B active): fast on CPU, needs ~12 GB RAM.
12 qwen2.5-coder:14b 9.0 11.5 no 40 Noticeably smarter than 7B; wants a GPU (~12 GB VRAM).
13 gpt-oss:20b 14 17 yes 50 MoE reasoning model; needs ~17 GB RAM or VRAM. MoE (Mixture of Experts) reasoning model; needs ~17 GB RAM or VRAM.
14 qwen3-coder:30b granite-code:34b 19 23 yes no 60 55 MoE (3B active): strong coder, fast on CPU with 24+ GB RAM. IBM, Apache-2.0 (fully permissive); dense, needs a 24 GB GPU.
15 devstral:24b 14 17 no 58 Mistral+All Hands, Apache-2.0; built for agentic multi-file edits, needs ~17 GB RAM or VRAM.
16 qwen3-coder:30b 19 23 yes 60 MoE (Mixture of Experts, 3B active): strong coder, fast on CPU with 24+ GB RAM.
17 qwen2.5-coder:32b 20 24 no 70 Top-quality dense coder; needs a 24 GB GPU.
setup.sh
+12 -2
View File
@@ -132,9 +132,12 @@ echo
# ------------------------------------------------ memory budget / context # ------------------------------------------------ memory budget / context
# What a model must fit into: VRAM when a GPU is used, else RAM minus headroom # What a model must fit into: VRAM when a GPU is used, else RAM minus headroom
# for the OS, aider and the editor. # for the OS, aider and the editor. hard_budget/gpu_hard have almost no headroom -
# a model only fitting there is "tight" (usable, but close other apps first).
budget=$(awk -v r="$ram_gb" 'BEGIN {b=r-4; if (b<1) b=1; printf "%.1f", b}') budget=$(awk -v r="$ram_gb" 'BEGIN {b=r-4; if (b<1) b=1; printf "%.1f", b}')
hard_budget=$(awk -v r="$ram_gb" 'BEGIN {b=r-1; if (b<1) b=1; printf "%.1f", b}')
gpu_budget=$(awk -v v="$vram_gb" 'BEGIN {printf "%.1f", v*0.9}') gpu_budget=$(awk -v v="$vram_gb" 'BEGIN {printf "%.1f", v*0.9}')
gpu_hard=$(awk -v v="$vram_gb" 'BEGIN {printf "%.1f", v*0.98}')
if awk -v b="$budget" 'BEGIN{exit !(b<6)}'; then CONTEXT=4096 if awk -v b="$budget" 'BEGIN{exit !(b<6)}'; then CONTEXT=4096
elif awk -v b="$budget" 'BEGIN{exit !(b>=40)}'; then CONTEXT=32768 elif awk -v b="$budget" 'BEGIN{exit !(b>=40)}'; then CONTEXT=32768
@@ -148,10 +151,14 @@ for i in "${!rows[@]}"; do
IFS=$'\t' read -r tag disk mem cpu_ok rank desc <<<"${rows[$i]}" IFS=$'\t' read -r tag disk mem cpu_ok rank desc <<<"${rows[$i]}"
tags[i]=$tag tags[i]=$tag
fits_ram=$(awk -v m="$mem" -v b="$budget" 'BEGIN{print (m<=b)}') fits_ram=$(awk -v m="$mem" -v b="$budget" 'BEGIN{print (m<=b)}')
fits_hard_ram=$(awk -v m="$mem" -v b="$hard_budget" 'BEGIN{print (m<=b)}')
fits_gpu=$(awk -v m="$mem" -v b="$gpu_budget" -v u="$gpu_usable" 'BEGIN{print (u && m<=b)}') fits_gpu=$(awk -v m="$mem" -v b="$gpu_budget" -v u="$gpu_usable" 'BEGIN{print (u && m<=b)}')
fits_hard_gpu=$(awk -v m="$mem" -v b="$gpu_hard" -v u="$gpu_usable" 'BEGIN{print (u && m<=b)}')
if [ "$fits_gpu" = 1 ]; then status[i]="fits"; speed[i]="fast (GPU)" if [ "$fits_gpu" = 1 ]; then status[i]="fits"; speed[i]="fast (GPU)"
elif [ "$fits_hard_gpu" = 1 ]; then status[i]="tight"; speed[i]="tight (GPU)"
elif [ "$fits_ram" = 1 ] && [ "$cpu_ok" = yes ]; then status[i]="fits"; speed[i]="ok (CPU)" elif [ "$fits_ram" = 1 ] && [ "$cpu_ok" = yes ]; then status[i]="fits"; speed[i]="ok (CPU)"
elif [ "$fits_ram" = 1 ]; then status[i]="slow"; speed[i]="slow (CPU)" elif [ "$fits_ram" = 1 ]; then status[i]="slow"; speed[i]="slow (CPU)"
elif [ "$fits_hard_ram" = 1 ]; then status[i]="tight"; speed[i]="tight (CPU)"
else status[i]="too big"; speed[i]="-"; fi else status[i]="too big"; speed[i]="-"; fi
[ "${status[$i]}" = fits ] && rec=$i # sorted by rank, so last "fits" wins [ "${status[$i]}" = fits ] && rec=$i # sorted by rank, so last "fits" wins
done done
@@ -211,7 +218,10 @@ if [ -z "$FORCE_MODEL" ]; then
[[ "$choice" =~ ^[0-9]+$ ]] && [ "$choice" -ge 1 ] && [ "$choice" -le "${#rows[@]}" ] || { echo "Invalid choice." >&2; exit 1; } [[ "$choice" =~ ^[0-9]+$ ]] && [ "$choice" -ge 1 ] && [ "$choice" -le "${#rows[@]}" ] || { echo "Invalid choice." >&2; exit 1; }
sel=$((choice-1)) sel=$((choice-1))
MODEL=${tags[$sel]} MODEL=${tags[$sel]}
if [ "${status[$sel]}" = "too big" ] || [ "${status[$sel]}" = "slow" ]; then if [ "${status[$sel]}" = "tight" ]; then
echo "Warning: $MODEL is 'tight' on this machine (fits, but leaves little headroom - close other apps first)."
if [ "$ASSUME_YES" != 1 ]; then read -r -p "Continue anyway? [y/N] " a; [[ "$a" =~ ^[Yy] ]] || exit 1; fi
elif [ "${status[$sel]}" = "too big" ] || [ "${status[$sel]}" = "slow" ]; then
echo "Warning: $MODEL is '${status[$sel]}' on this machine (may swap, crawl, or crash)." echo "Warning: $MODEL is '${status[$sel]}' on this machine (may swap, crawl, or crash)."
if [ "$ASSUME_YES" != 1 ]; then read -r -p "Continue anyway? [y/N] " a; [[ "$a" =~ ^[Yy] ]] || exit 1; fi if [ "$ASSUME_YES" != 1 ]; then read -r -p "Continue anyway? [y/N] " a; [[ "$a" =~ ^[Yy] ]] || exit 1; fi
fi fi