unsloth / text-generation updated 1 year ago

mistral-7b-v0.3-bnb-4bit

Name: mistral-7b-v0.3-bnb-4bit
Author: unsloth

We have a Google Colab Tesla T4 notebook for Mistral v3 7b here: https://colab.research.google.com/drive/1yNCks4BTD5zOnjozppphh5GzMFaMKq?usp=sharing

Params

7.5 B

Context

32,768

Downloads 30d

380 K

Likes

Commercial use: allowed apache-2.0 Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

381 K372 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	u8	4.1 GB	6.2 GB	✅ Runs comfortably
model.safetensors (bf16, full)	bf16 + 32K ctx	4.1 GB	9.5 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/mistral-7b-v0-3-bnb-4bit
{
  "hf_id": "unsloth/mistral-7b-v0.3-bnb-4bit",
  "params_b": 7.47,
  "context_length": 32768,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 380476,
  "vram_estimates": [
    { "quant": "u8", "gb": 6.2 }
  ],
  "updated_at": "2026-07-28T18:06:02Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture: MistralForCausalLM
Parameters: 7.5 B
Tensor type: U8
Context length: 32,768
Vocabulary: 32,768
Layers / heads: 32 / 32
Licence: apache-2.0
First seen on the Hub: 2024-05-22
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with

Qwen3-8B 16.3 M Qwen2.5-7B-Instruct 12.1 M Qwen3.6-35B-A3B-NVFP4 11.3 M Llama-3.1-8B-Instruct 8.0 M Qwen2.5-7B-Instruct-AWQ 4.6 M granite-4.1-8b 4.2 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB