rekiniasty/ qwen3.5:122b-a10b-mlx-int4

69 1 week ago

Based on Qwen3.5-122B-A10B and converted from the MLX Community 4-bit release (https://huggingface.co/mlx-community/Qwen3.5-122B-A10B-4bit)

vision tools thinking
ollama run rekiniasty/qwen3.5:122b-a10b-mlx-int4

Details

1 week ago

52996c6fd966 · 70GB ·

{ "architectures": [ "Qwen3_5MoeForConditionalGeneration" ], "eos_token_id": [ 248046, 248044 ], "im
{ "bos_token_id": 248044, "do_sample": true, "eos_token_id": [ 248046, 248044 ], "pad_token_id": 248
{ "size": { "longest_edge": 16777216, "shortest_edge": 65536 }, "patch_size": 16, "temporal_patch_si
{ "image_processor": { "data_format": "channels_first", "do_convert_rgb": true, "do_normalize": true
{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 248044, "content"
{ "add_prefix_space": false, "audio_bos_token": "<|audio_start|>", "audio_eos_token": "<|audio_end|>
{ "size": { "longest_edge": 25165824, "shortest_edge": 4096 }, "patch_size": 16, "temporal_patch_siz
{ "!": 0, "\"": 1, "#": 2, "$": 3, "%": 4, "&": 5, "'": 6, "(": 7, ")": 8, "*": 9, "+": 10, ",": 11,
Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR US
{ "min_p": 0, "presence_penalty": 1.5, "repeat_penalty": 1, "temperature": 1, "t
{{ .Prompt }}
1212 tensors

Readme

Qwen3.5 122B A10B 4bit

Qwen3.5-122B-A10B quantized to 4-bit for efficient local deployment. Delivers strong reasoning, coding, and multilingual capabilities while significantly reducing memory requirements.

Source

Based on Qwen3.5-122B-A10B and converted from the MLX Community 4-bit release. https://huggingface.co/mlx-community/Qwen3.5-122B-A10B-4bit