Check my GPU

LLMs ·

StableLM 2 Zephyr 1.6B

Parameters
1.6B
Architecture
Dense
Max context
4K tokens
License
stabilityai-non-commercial
Released
2024-01

How to run it

Quickest · Ollama

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

ollama run stablelm2:1.6b-zephyr

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/stabilityai/stablelm-2-zephyr-1_6b (opens in a new tab)

ollama run hf.co/stabilityai/stablelm-2-zephyr-1_6b

Original weights · Hugging Face

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

huggingface.co/stabilityai/stablelm-2-zephyr-1_6b (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 0.7 GB 2.1 GB
Q3_K_M Low 0.8 GB 2.2 GB
Q4_K_M Good 1.0 GB 2.4 GB GGUF (Q4_0) (opens in a new tab)
Q5_K_M High 1.2 GB 2.6 GB GGUF (opens in a new tab)
Q6_K High 1.3 GB 2.8 GB
Q8_0 Very high 1.7 GB 3.1 GB GGUF (opens in a new tab)
F16 Full 3.3 GB 4.7 GB Original weights (opens in a new tab)

Best hardware for StableLM 2 Zephyr 1.6B

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc A380 (launch price $139) at Q8_0.

Grade · points Hardware Quant Memory Speed Fit
59 ptsGood (B) · 59 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.7/15 NVIDIA GeForce RTX 4060 F16 5.1 GB / 8.0 GB 47.8 tok/s Runs well
54 ptsUsable (C) · 54 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.2/15 Intel Arc B580 F16 5.3 GB / 12.0 GB 61.2 tok/s Runs well
54 ptsUsable (C) · 54 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.2/15 NVIDIA GeForce RTX 3060 12GB F16 5.3 GB / 12.0 GB 63.2 tok/s Runs well
54 ptsUsable (C) · 54 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.2/15 NVIDIA GeForce RTX 4070 SUPER F16 5.3 GB / 12.0 GB 88.5 tok/s Runs well
53 ptsUsable (C) · 53 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.6/15 Apple M4 Pro (24 GB) F16 6.0 GB / 16.1 GB 41.3 tok/s Runs well
52 ptsUsable (C) · 52 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.9/15 AMD Radeon RX 9070 XT F16 5.5 GB / 16.0 GB 96.8 tok/s Runs well
52 ptsUsable (C) · 52 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.9/15 NVIDIA GeForce RTX 4060 Ti 16GB F16 5.5 GB / 16.0 GB 50.6 tok/s Runs well
52 ptsUsable (C) · 52 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.9/15 NVIDIA GeForce RTX 4070 Ti SUPER F16 5.5 GB / 16.0 GB 118 tok/s Runs well
52 ptsUsable (C) · 52 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.9/15 NVIDIA GeForce RTX 4080 SUPER F16 5.5 GB / 16.0 GB 129 tok/s Runs well
52 ptsUsable (C) · 52 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.9/15 NVIDIA GeForce RTX 5060 Ti 16GB F16 5.5 GB / 16.0 GB 78.7 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.