What are the hardware requirements for Mistral Medium 3.5 128B GGUF?

Mistral Medium 3.5 128B GGUF requires approximately 5.4 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Mistral Medium 3.5 128B GGUF and how large is it?

Mistral Medium 3.5 128B GGUF is developed by unsloth, a model with 128b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Mistral Medium 3.5 128B GGUF perform on standard benchmarks?

Mistral Medium 3.5 128B GGUF has the following published scores: LMSYS ELO 1410. Compare against reference models on this page or on the LLM Explorer leaderboards.

Mistral Medium 3.5 128B GGUF by unsloth — VRAM 5.4GB

Name: Mistral Medium 3.5 128B GGUF
Author: unsloth

Mistral Medium 3.5 128B GGUF is an open-source language model by unsloth. Features: 128b LLM, VRAM: 5.4GB, License: other, Quantized, LLM Explorer Score: 0.46, ELO: 1410.

Ar Base model:mistralai/mistral-m... Base model:quantized:mistralai... Bn Conversational De En Endpoints compatible Es Fa Fp8 Fr Gguf Hi Id Imatrix It Ja Ko Mistral Mistral3 Ms Ne Pl Pt Q2 Quantized Region:us Ro Ru Sr Sv Tr Uk Unsloth Vi Zh

Model Card on HF 🤗: https://huggingface.co/unsloth/Mistral-Medium-3.5-128B-GGUF

Mistral Medium 3.5 128B GGUF Benchmarks

LMSys ELO 1410 vs 1272 (so35) 10.8%

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

Mistral Medium 3.5 128B GGUF Parameters and Internals

LLM Name	Mistral Medium 3.5 128B GGUF
Repository 🤗	https://huggingface.co/unsloth/Mistral-Medium-3.5-128B-GGUF
Base Model(s)	mistralai/Mistral-Medium-3.5-128B mistralai/Mistral-Medium-3.5-128B
Model Size	128b
Required VRAM	5.4 GB
Updated	2026-07-22
Maintainer	unsloth
Model Type	mistral3
Model Files	46.6 GB 47.0 GB 44.1 GB 34.9 GB 49.3 GB 48.1 GB 5.4 GB 5.4 GB 10.7 GB
Supported Languages	en fr de es pt it ja ko ru zh ar fa id ms ne pl ro sr sv tr uk vi hi bn
GGUF Quantization	Yes
Quantization Type	gguf\|q2
Model Architecture	Mistral3ForConditionalGeneration
License	other
Transformers Version	5.7.0.dev0
Torch Data Type	bfloat16

Rank the Mistral Medium 3.5 128B GGUF 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 Mistral Medium 3.5 128B GGUF

Best Alternatives	Context / RAM	Downloads	Likes
Tosilos 128B	0K / 255.4 GB	60	8
Mistral Medium 3.5 128B BF16	0K / 254.9 GB	3372	0