What are the hardware requirements for Tinymistral V2 Pycoder Instruct 248M?

Tinymistral V2 Pycoder Instruct 248M requires approximately 1 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 Tinymistral V2 Pycoder Instruct 248M and how large is it?

Tinymistral V2 Pycoder Instruct 248M is developed by jtatman, a model with 248m 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 Tinymistral V2 Pycoder Instruct 248M?

Tinymistral V2 Pycoder Instruct 248M is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Tinymistral V2 Pycoder Instruct 248M by jtatman — VRAM 1GB, 32K context

Name: Tinymistral V2 Pycoder Instruct 248M
Author: jtatman

Tinymistral V2 Pycoder Instruct 248M is an open-source language model by jtatman. Features: 248m LLM, VRAM: 1GB, Context: 32K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.11.

Code Dataset:jtatman/pile python in... Dataset:jtatman/python-code-da... Dataset:jtatman/python-github-... Endpoints compatible Instruct Mistral Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/jtatman/tinymistral-v2-pycoder-instruct-248m

Tinymistral V2 Pycoder Instruct 248M Parameters and Internals

Model Type

MistralForCausalLM

Use Cases

Primary Use Cases:

Generate python code.

Additional Notes

Model is in active development, base model is in active development, and all should be treated with caution.

Training Details

Data Sources:

jtatman/python-code-dataset-500k, jtatman/python-github-code-instruct-filtered-5k, jtatman/pile_python_instruct_format

Methodology:

Conversion to alpaca/instruct format.

LLM Name	Tinymistral V2 Pycoder Instruct 248M
Repository 🤗	https://huggingface.co/jtatman/tinymistral-v2-pycoder-instruct-248m
Model Size	248m
Required VRAM	1 GB
Updated	2026-07-22
Maintainer	jtatman
Model Type	mistral
Instruction-Based	Yes
Model Files	1.0 GB
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.36.2
Tokenizer Class	LlamaTokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	32009
Torch Data Type	float32

Rank the Tinymistral V2 Pycoder Instruct 248M 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 Tinymistral V2 Pycoder Instruct 248M

Best Alternatives	Context / RAM	Downloads	Likes
TinyMistral 248M V2.5 Instruct	32K / 1 GB	2	11
...adrin TinyMistral248M Instruct	32K / 0.5 GB	108	7
TinyMistral 248M Instruct	32K / 1 GB	69	12
Tinymistv1	32K / 0.5 GB	17	0
...istral 248M V2.5 Instruct Orpo	32K / 0.5 GB	6	0
TinyMistral 248M V2 Instruct	32K / 0.5 GB	159	7
...mistral 248M Hypnosis Instruct	32K / 0.5 GB	4	2
...al V2 Pycoder Instruct 248M V1	32K / 0.5 GB	11	1
...istral Magicoder Instruct 248M	32K / 0.5 GB	6	2
Tinymistv1	32K / 0.5 GB	0	0

Note: green Score (e.g. "73.2") means that the model is better than jtatman/tinymistral-v2-pycoder-instruct-248m.