Check my GPU

LLMs ·

Mistral 7B Instruct v0.2

Parameters
7.2B
Architecture
Dense
Max context
32K tokens
License
apache-2.0
Released
2023-12

How to run it

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

ollama run mistral:7b-instruct-v0.2-q4_K_M

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-i1-GGUF (opens in a new tab)

ollama run hf.co/mradermacher/Mistral-7B-Instruct-v0.2-i1-GGUF

Original weights · Hugging Face

Full-precision files from Mistral AI, for fine-tuning, vLLM, Transformers.

huggingface.co/mistralai/Mistral-7B-Instruct-v0.2 (opens in a new tab)

No sign-in needed.

Links checked 5 days ago against Hugging Face, Ollama and GitHub.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps.

Quantization Quality Weights Total at 8K context Total at 32K context Download
Q2_K Low 2.9 GB 4.6 GB 7.8 GB GGUF (opens in a new tab)
Q3_K_M Low 3.5 GB 5.2 GB 8.4 GB GGUF (opens in a new tab)
Q4_K_M Good 4.4 GB 6.1 GB 9.3 GB GGUF (opens in a new tab)
Q5_K_M High 5.1 GB 6.8 GB 10.0 GB GGUF (opens in a new tab)
Q6_K High 5.9 GB 7.6 GB 10.8 GB GGUF (opens in a new tab)
Q8_0 Very high 7.7 GB 9.3 GB 12.6 GB
F16 Full 14.5 GB 16.2 GB 19.4 GB Original weights (opens in a new tab)

Best hardware for Mistral 7B Instruct v0.2

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc A380 (launch price $139) at Q2_K.

Grade · points Hardware Quant Memory Speed Fit
70 ptsGood (B) · 70 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4090 F16 17.4 GB / 24.0 GB 40.1 tok/s Runs well
70 ptsGood (B) · 70 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4070 SUPER Q8_0 9.9 GB / 12.0 GB 43.5 tok/s Runs well
70 ptsGood (B) · 70 of 100 points: Model quality 15.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 Intel Arc B580 Q6_K 8.2 GB / 12.0 GB 41.0 tok/s Runs well
70 ptsGood (B) · 70 of 100 points: Model quality 15.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 3060 12GB Q6_K 8.2 GB / 12.0 GB 42.4 tok/s Runs well
69 ptsGood (B) · 69 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.6/15 AMD Radeon RX 9070 XT Q8_0 10.1 GB / 16.0 GB 47.6 tok/s Runs well
69 ptsGood (B) · 69 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.6/15 NVIDIA GeForce RTX 4070 Ti SUPER Q8_0 10.1 GB / 16.0 GB 58.0 tok/s Runs well
69 ptsGood (B) · 69 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.6/15 NVIDIA GeForce RTX 4080 SUPER Q8_0 10.1 GB / 16.0 GB 63.5 tok/s Runs well
69 ptsGood (B) · 69 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.6/15 NVIDIA GeForce RTX 5070 Ti Q8_0 10.1 GB / 16.0 GB 77.3 tok/s Runs well
69 ptsGood (B) · 69 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.6/15 NVIDIA GeForce RTX 5080 Q8_0 10.1 GB / 16.0 GB 82.9 tok/s Runs well
69 ptsGood (B) · 69 of 100 points: Model quality 14.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4060 Q4_K_M 6.5 GB / 8.0 GB 46.1 tok/s Runs well

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.