uptonking

uptonking's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in unsloth/Qwen3.5-9B-MTP-GGUF 2 months ago

Is using MTP actually slower?

👍 6

4

#4 opened 2 months ago by

jian2023

New activity in unsloth/gemma-4-31b-it-UD-MLX-4bit 3 months ago

why is this model not found in LM Studio model search result?

👍 1

#2 opened 3 months ago by

uptonking

New activity in RepublicOfKorokke/Qwen3.5-35B-A3B-mlx-lm-mxfp4 3 months ago

can we have a Qwen3.6-35B-A3B-mlx-lm-mxfp4

1

#2 opened 3 months ago by

uptonking

New activity in ibm-granite/granite-4.0-3b-vision 4 months ago

share a usable chat template in lm studio

#6 opened 4 months ago by

uptonking

New activity in prithivMLmods/chandra-ocr-2-GGUF 4 months ago

Can you add Q4 families?

4

#1 opened 4 months ago by

sdve

New activity in mlx-community/GLM-4.7-Flash-4bit-mxfp4 6 months ago

why is this mlx model almost unusable with looping in lm studio

#1 opened 6 months ago by

uptonking

New activity in lmstudio-community/GLM-4.7-Flash-MLX-8bit 6 months ago

The model gets stuck in a loop and starts writing all sorts of nonsense.

1

#1 opened 6 months ago by

amaycom

New activity in tencent/HY-MT1.5-7B 7 months ago

协议=

1

#1 opened 7 months ago by

LittleTaro

New activity in ExaltedSlayer/mistralai-devstral-small-2-24b-instruct-2512-mlx-mxfp4 8 months ago

failed to load in lm studio - ValueError: Tokenizer class TokenizersBackend does not exist or is not currently imported

👀 1

2

#1 opened 8 months ago by

uptonking

New activity in lmstudio-community/gemma-3-270m-it-qat-MLX-4bit 9 months ago

this one and the other 4-bit quant went into a whole the shining thign for me...

1

#1 opened 12 months ago by

acoliver

New activity in mlx-community/Qwen3-VL-30B-A3B-Thinking-4bit 10 months ago

when i use this model in lm studio, the error is `error in iterating prediction stream: valueerror: image features and image tokens do not match`

👍 1

2

#1 opened 10 months ago by

uptonking

New activity in ai21labs/AI21-Jamba-Reasoning-3B 10 months ago

when using AI21-Jamba-Reasoning-3B-GGUF `Q4_K_M` in lm studio, why does the collapsible thinking ui not show?

5

#6 opened 10 months ago by

uptonking

New activity in bralynn/pydevmini1 10 months ago

when using this model on lm studio, why no collapsible thinking section ui?

#1 opened 10 months ago by

uptonking

New activity in mrtoots/unsloth-Magistral-Small-2509-mlx-8Bit 11 months ago

8bit is too large, Could we have a unsloth-Magistral-Small-2509-mlx-4Bit please ❤️

1

#1 opened 11 months ago by

uptonking