Check my GPU

LLMs ·

CodeGemma 2B

Parameters
2.5B
Architecture
Dense
Max context
8K tokens
License
gemma
Released
2024-03

How to run it

Quickest · Ollama

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

ollama run codegemma:2b

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/google/codegemma-2b-GGUF (opens in a new tab)

ollama run hf.co/google/codegemma-2b-GGUF

Original weights · Hugging Face

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

huggingface.co/google/codegemma-2b (opens in a new tab)

Free Hugging Face account needed: request access on the model page, and Google approves it (usually within minutes to a few hours).

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 Download
Q2_K Low 1.0 GB 1.8 GB
Q3_K_M Low 1.2 GB 2.0 GB
Q4_K_M Good 1.5 GB 2.3 GB
Q5_K_M High 1.8 GB 2.5 GB
Q6_K High 2.1 GB 2.8 GB
Q8_0 Very high 2.7 GB 3.4 GB
F16 Full 5.0 GB 5.8 GB GGUF (opens in a new tab) Original weights (opens in a new tab)

Best hardware for CodeGemma 2B

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc A380 (launch price $139) at Q6_K.

Grade · points Hardware Quant Memory Speed Fit
58 ptsGood (B) · 58 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.3/15 NVIDIA GeForce RTX 3060 12GB F16 6.4 GB / 12.0 GB 41.3 tok/s Runs well
58 ptsGood (B) · 58 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.3/15 NVIDIA GeForce RTX 4070 SUPER F16 6.4 GB / 12.0 GB 57.8 tok/s Runs well
57 ptsUsable (C) · 57 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.0/15 NVIDIA GeForce RTX 4060 Q8_0 3.8 GB / 8.0 GB 67.7 tok/s Runs well
55 ptsUsable (C) · 55 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.5/15 AMD Radeon RX 9070 XT F16 6.6 GB / 16.0 GB 63.2 tok/s Runs well
55 ptsUsable (C) · 55 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.5/15 NVIDIA GeForce RTX 4070 Ti SUPER F16 6.6 GB / 16.0 GB 77.1 tok/s Runs well
55 ptsUsable (C) · 55 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.5/15 NVIDIA GeForce RTX 4080 SUPER F16 6.6 GB / 16.0 GB 84.4 tok/s Runs well
55 ptsUsable (C) · 55 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.5/15 NVIDIA GeForce RTX 5060 Ti 16GB F16 6.6 GB / 16.0 GB 51.4 tok/s Runs well
55 ptsUsable (C) · 55 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.5/15 NVIDIA GeForce RTX 5070 Ti F16 6.6 GB / 16.0 GB 103 tok/s Runs well
55 ptsUsable (C) · 55 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.5/15 NVIDIA GeForce RTX 5080 F16 6.6 GB / 16.0 GB 110 tok/s Runs well
54 ptsUsable (C) · 54 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.7/15 Intel Arc B580 Q8_0 4.0 GB / 12.0 GB 86.7 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.