What are the hardware requirements for Sky T1 Coder 32B Flash?

Sky T1 Coder 32B Flash requires approximately 65.8 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Sky T1 Coder 32B Flash and how large is it?

Sky T1 Coder 32B Flash is developed by tomasmcm, a model with 32b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Sky T1 Coder 32B Flash?

Sky T1 Coder 32B Flash is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Sky T1 Coder 32B Flash by tomasmcm — VRAM 65.8GB, 32K context

Name: Sky T1 Coder 32B Flash
Author: tomasmcm

Sky T1 Coder 32B Flash is an open-source language model by tomasmcm. Features: 32b LLM, VRAM: 65.8GB, Context: 32K, License: apache-2.0, Code Generating, Merged, LLM Explorer Score: 0.29.

Merged Model Arxiv:2408.07990 Base model:novasky-ai/sky-t1-3... Base model:qwen/qwen2.5-coder-... Base model:qwen/qwen2.5-coder-... Codegen Conversational Endpoints compatible Qwen2 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/tomasmcm/sky-t1-coder-32b-flash

Sky T1 Coder 32B Flash Parameters and Internals

LLM Name	Sky T1 Coder 32B Flash
Repository 🤗	https://huggingface.co/tomasmcm/sky-t1-coder-32b-flash
Base Model(s)	Qwen/Qwen2.5-Coder-32B-Instruct Sky T1 32B Flash Qwen/Qwen2.5-Coder-32B Qwen/Qwen2.5-Coder-32B-Instruct NovaSky-AI/Sky-T1-32B-Flash Qwen/Qwen2.5-Coder-32B
Merged Model	Yes
Model Size	32b
Required VRAM	65.8 GB
Updated	2026-07-30
Maintainer	tomasmcm
Model Type	qwen2
Model Files	5.0 GB: 1-of-14 5.0 GB: 2-of-14 4.9 GB: 3-of-14 4.9 GB: 4-of-14 4.9 GB: 5-of-14 4.9 GB: 6-of-14 4.9 GB: 7-of-14 4.9 GB: 8-of-14 4.9 GB: 9-of-14 4.9 GB: 10-of-14 4.9 GB: 11-of-14 4.9 GB: 12-of-14 4.9 GB: 13-of-14 1.9 GB: 14-of-14
Generates Code	Yes
Model Architecture	Qwen2ForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.48.2
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	152064
Torch Data Type	bfloat16
Errors	replace

Rank the Sky T1 Coder 32B Flash capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Sky T1 Coder 32B Flash

Best Alternatives	Context / RAM	Downloads	Likes
...y Qwen2.5coder 32B V24.1q 200K	195K / 65.8 GB	9	2
...2.5 Godzilla Coder V2 51B 128K	128K / 102.1 GB	8	1
Qwen2.5 32B YOYO V2	128K / 65.7 GB	11	1
QwQ Coder R1 Distill 32B	128K / 65.8 GB	8	0
Qwen2.5 32B YOYO MIX	128K / 65.7 GB	8	2
Qwen2.5 Coder 32B YOYO	128K / 65.8 GB	8	2
YOYO O1 32B V2	128K / 65.7 GB	6	3
QwQ Coder 32B	128K / 65.7 GB	10	7
QwQ Qwen2.5 Coder Instruct 32B	128K / 65.8 GB	43	0
Reasoning TIES Coder V1.1	128K / 65.7 GB	15	2