qwen3.8:27b-mlx

Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks.

Details

Updated 3 hours ago

3 hours ago

5642e97495e1 · 18GB ·

json

{ "architectures": [ "Qwen3_5ForConditionalGeneration" ], "image_token_id": 248056, "language_model_

80kB

json

{ "bos_token_id": 248044, "do_sample": true, "eos_token_id": [ 248046, 248044 ], "pad_token_id": 248

202B

json

{ "producer": { "name": "modelopt", "version": "0.0.0" }, "quantization": { "quant_algo": "MIXED_PRE

62kB

json

{ "size": { "longest_edge": 16777216, "shortest_edge": 65536 }, "patch_size": 16, "temporal_patch_si

390B

json

{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 248044, "content"

13MB

json

{ "add_prefix_space": false, "added_tokens_decoder": { "248044": { "content": "<|endoftext|>", "lstr

18kB

json

{ "size": { "longest_edge": 25165824, "shortest_edge": 4096 }, "patch_size": 16, "temporal_patch_siz

385B

json

{ "!": 0, "\"": 1, "#": 2, "$": 3, "%": 4, "&": 5, "'": 6, "(": 7, ")": 8, "*": 9, "+": 10, ",": 11,

6.7MB

license

Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR US

11kB

params

{ "min_p": 0, "presence_penalty": 0, "repeat_penalty": 1, "temperature": 1, "top

92B

1199 tensors

18GB

Qwen3.8 Highlights

Qwen3.8-27B features the following enhancements:

Core Capabilities: Comprehensive improvements across coding, professional work, research, and long-horizon agentic tasks.
Agent Execution: Stronger autonomous planning and better handling of environment feedback, leading to more reliable end-to-end task completion.
Downstream Compatibility: Broader support for popular harnesses and development tools, making it easier to integrate into your existing stack.
Flexible Thinking Control: Thinking mode is on by default and can be disabled per request; reasoning depth can be tuned with reasoning_effort, and reasoning context from historical messages is retained via preserve_thinking.
Vision-Language Understanding: Native support for image and video understanding, from STEM diagrams and documents to hour-scale videos.