colin/nix-files
1
0
Fork 1
Code Issues Pull Requests Projects Releases Wiki Activity

ollama: ship a bunch of new models

Browse Source
This commit is contained in:
Colin
2025-07-24 19:53:17 +00:00
parent 7b66e2f0e2
commit e2a183e8d3
18 changed files with 302 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
modules/services/ollama.nix
View File

@@ -40,11 +40,17 @@ let
deepseek-r1-abliterated-14b
deepseek-r1-abliterated-32b
deepseek-r1-abliterated-70b
dolphin-mistral-7b # UNCENSORED mistral; compliant
dolphin-mixtral-8x7b # about as fast as a 14b model, similar quality results. uncensored, but still preachy
devstral-24b
dolphin3-8b
# dolphin-mistral-7b # UNCENSORED mistral; compliant
# dolphin-mixtral-8x7b # about as fast as a 14b model, similar quality results. uncensored, but still preachy
# falcon2-11b # code examples are lacking
# gemma2-9b # fast, but not great for code
gemma2-27b # generates at 1word/sec, but decent coding results if you can wrangle it
# gemma2-27b # generates at 1word/sec, but decent coding results if you can wrangle it
gemma3-12b
gemma3-27b
gemma3n-e2b
gemma3n-e4b
# glm4-9b # it generates invalid code
# hermes3-8b # FAST, but unwieldy
# llama3-chatqa-8b # it gets stuck
@@ -54,15 +60,25 @@ let
# llama3_3-70b # non-compliant; dodges iffy questions
llama3_3-abliterated-70b # compliant, but slower and not as helpful as deepseek-r1-abliterated-70b
magicoder-7b # it generates valid, if sparse, code
magistral-24b
marco-o1-7b # untested
# mistral-7b # it generates invalid code
# mistral-nemo-12b # it generates invalid code
mistral-small-22b # quality comparable to qwen2_5
# mistral-small-22b # quality comparable to qwen2_5
mistral-small3_2-24b
# mistral-large-123b # times out launch on desko
# mixtral-8x7b # generates valid, if sparse, code; only for the most popular languages
olmo2-13b
openthinker-7b
openthinker-32b
orca-mini-7b
# phi3_5-3b # generates invalid code
phi4-14b
# qwen2_5-7b # notably less quality than 32b (i.e. generates invalid code)
qwen2_5-14b # *almost* same quality to 32b variant, but faster
# qwen2_5-14b # *almost* same quality to 32b variant, but faster
qwen3-8b
qwen3-14b
qwen3-30b
# qwen2_5-32b-instruct-q2_K # lower-res version of default 32b (so, slightly faster, but generates invalid code where the full res generates valid code)
qwen2_5-32b # generates 3~5 words/sec, but notably more accurate than coder-7b
qwen2_5-abliterate-7b