Cli list models

[agolokoz]

> cli list-models

Name	ID
Qwen3.5 0.8B	qwen3.5:0.8b
Qwen3.5 2B	qwen3.5:2b
Qwen3.5 4B	qwen3.5:4b
Gemma-3 270M Functiongemma-it	gemma-3:270m:functiongemma-it
Gemma-3 1B It	gemma-3:1b:it
Gemma-3 4B It	gemma-3:4b:it
Gemma-3 27B It	gemma-3:27b:it
GPT-OSS 20B	gpt-oss:20b
LFM2 350M	lfm2:350m
LFM2 0.7B	lfm2:0.7b
LFM2 1.2B	lfm2:1.2b
LFM2 2.6B	lfm2:2.6b
LFM2.5 350M	lfm2.5:350m
LFM2.5 1.2B Instruct	lfm2.5:1.2b:instruct
LFM2.5 1.2B Thinking	lfm2.5:1.2b:thinking
Llama-3.2 1B Instruct	llama-3.2:1b:instruct
Llama-3.2 3B Instruct	llama-3.2:3b:instruct
Qwen3 0.6B	qwen3:0.6b
Qwen3 1.7B	qwen3:1.7b
Qwen3 4B	qwen3:4b
Qwen3 4B Instruct-2507	qwen3:4b:instruct-2507
Qwen3 4B Thinking-2507	qwen3:4b:thinking-2507
Qwen3 8B	qwen3:8b
Qwen3 14B	qwen3:14b
Qwen3 32B	qwen3:32b
Qwen3.5 9B	qwen3.5:9b
Qwen3.5 27B	qwen3.5:27b
Qwen3.6 27B	qwen3.6:27b

> cli list-checkpoints qwen3.5:4b

Name	ID
Qwen3.5 4B Mirai Medium Quantization	alibaba:qwen3.5:4b:mirai:mirai-m:4
Qwen3.5 4B Mirai Large Quantization	alibaba:qwen3.5:4b:mirai:mirai-l:8
Qwen3.5 4B	alibaba:qwen3.5:4b
Qwen3.5 4B MLX 4-bit	alibaba:qwen3.5:4b:mlx-community:mlx:4
Qwen3.5 4B MLX 8-bit	alibaba:qwen3.5:4b:mlx-community:mlx:8

How cli --model ${MODEL} resolves:

qwen3.5  -> alibaba:qwen3.5:4b:mirai:mirai-m:4
gemma-3  -> google:gemma-3:27b:it
gpt-oss  -> openai:gpt-oss:20b
lfm2     -> liquidai:lfm2:2.6b
lfm2.5   -> liquidai:lfm2.5:1.2b:instruct
llama-3.2 -> meta:llama-3.2:3b:instruct
qwen3    -> alibaba:qwen3:32b
qwen3.6  -> alibaba:qwen3.6:27b

[agolokoz]

@codex review

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: d48395b962

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".