Check my GPU

LLMs ·

Vicuna 13B v1.5

Parameters
13B
Architecture
Dense
Max context
4K tokens
License
llama2
Released
2023-07

How to run it

Quickest · Ollama

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

ollama run vicuna:13b

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/QuantFactory/vicuna-13b-v1.5-GGUF (opens in a new tab)

ollama run hf.co/QuantFactory/vicuna-13b-v1.5-GGUF

Original weights · Hugging Face

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

huggingface.co/lmsys/vicuna-13b-v1.5 (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 4K context Download
Q2_K Low 5.2 GB 9.2 GB GGUF (opens in a new tab)
Q3_K_M Low 6.4 GB 10.3 GB GGUF (opens in a new tab)
Q4_K_M Good 7.9 GB 11.9 GB GGUF (opens in a new tab)
Q5_K_M High 9.2 GB 13.2 GB GGUF (opens in a new tab)
Q6_K High 10.7 GB 14.6 GB GGUF (opens in a new tab)
Q8_0 Very high 13.8 GB 17.8 GB GGUF (opens in a new tab)
F16 Full 26.0 GB 30.0 GB Original weights (opens in a new tab)

Best hardware for Vicuna 13B v1.5

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc B570 (launch price $219) at Q2_K.

Grade · points Hardware Quant Memory Speed Fit
64 ptsGood (B) · 64 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 3090 Q8_0 19.0 GB / 24.0 GB 44.9 tok/s Runs well
64 ptsGood (B) · 64 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4090 Q8_0 19.0 GB / 24.0 GB 48.4 tok/s Runs well
63 ptsGood (B) · 63 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 14.9/15, Memory use 15.0/15 AMD Radeon RX 7900 XTX Q8_0 19.0 GB / 24.0 GB 39.7 tok/s Runs well
63 ptsGood (B) · 63 of 100 points: Model quality 8.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 AMD Radeon RX 9070 XT Q4_K_M 12.7 GB / 16.0 GB 52.0 tok/s Runs well
63 ptsGood (B) · 63 of 100 points: Model quality 8.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4070 Ti SUPER Q4_K_M 12.7 GB / 16.0 GB 63.4 tok/s Runs well
63 ptsGood (B) · 63 of 100 points: Model quality 8.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4080 SUPER Q4_K_M 12.7 GB / 16.0 GB 69.4 tok/s Runs well
63 ptsGood (B) · 63 of 100 points: Model quality 8.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5060 Ti 16GB Q4_K_M 12.7 GB / 16.0 GB 42.2 tok/s Runs well
63 ptsGood (B) · 63 of 100 points: Model quality 8.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5070 Ti Q4_K_M 12.7 GB / 16.0 GB 84.5 tok/s Runs well
63 ptsGood (B) · 63 of 100 points: Model quality 8.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5080 Q4_K_M 12.7 GB / 16.0 GB 90.5 tok/s Runs well
62 ptsGood (B) · 62 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.0/15 NVIDIA GeForce RTX 5090 Q8_0 19.4 GB / 32.0 GB 86.0 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.