Check my GPU

on

Can the NVIDIA GeForce RTX 4090 run Code Llama 7B Instruct?

65 ptsGood (B) · 65 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15

Yes, it runs well

Runs well. At F16 it needs about 19.6 GB of 24.0 GB usable, with an estimated speed of 43.1 tok/s.

Best quant
F16
Generation speed
43.1 tok/s
Prompt processing
8,824 tok/s
First token (1K prompt)
0.3 s
Largest safe context
16K

Download Code Llama 7B Instruct

Recommended for the NVIDIA GeForce RTX 4090: F16. Every other quantization has its own download link in the table below.

Quickest · Ollama

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

ollama run codellama:7b-instruct-fp16

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/TheBloke/CodeLlama-7B-Instruct-GGUF (opens in a new tab)

ollama run hf.co/TheBloke/CodeLlama-7B-Instruct-GGUF

Original weights · Hugging Face

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

huggingface.co/meta-llama/CodeLlama-7b-Instruct-hf (opens in a new tab)

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

Official repo · GitHub

Reference code, inference scripts and docs from Meta. The weights themselves download from Hugging Face.

github.com/meta-llama/codellama (opens in a new tab)

git clone https://github.com/meta-llama/codellama

Meta’s official Code Llama repo.

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

How the B grade is scored

Every result gets up to 100 points from four parts. The points decide the letter grade.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.10.8 / 45
Memory fitFull marks when everything sits in GPU or unified memory; fewer when part spills to system RAM.25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.15.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.15.0 / 15
Total65.8 / 10065 ptsGood (B) · 65 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15

Grade scale: S 85+ · A 72+ · B 58+ · C 42+ · D 25+ · F under 25 points.

Every quantization on the NVIDIA GeForce RTX 4090

Quant Memory needed Available Speed Fit Grade · points Download
Q2_K 8.8 GB 24.0 GB 302 tok/s Runs well 56 ptsUsable (C) · 56 of 100 points: Model quality 7.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.5/15 GGUF (opens in a new tab)
Q3_K_M 9.4 GB 24.0 GB 237 tok/s Runs well 58 ptsGood (B) · 58 of 100 points: Model quality 9.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.0/15 GGUF (opens in a new tab)
Q4_K_M 10.2 GB 24.0 GB 184 tok/s Runs well 60 ptsGood (B) · 60 of 100 points: Model quality 10.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.8/15 GGUF (opens in a new tab)
Q5_K_M 10.9 GB 24.0 GB 152 tok/s Runs well 60 ptsGood (B) · 60 of 100 points: Model quality 10.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.5/15 GGUF (opens in a new tab)
Q6_K 11.6 GB 24.0 GB 127 tok/s Runs well 61 ptsGood (B) · 61 of 100 points: Model quality 10.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.2/15 GGUF (opens in a new tab)
Q8_0 13.2 GB 24.0 GB 93.5 tok/s Runs well 63 ptsGood (B) · 63 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.7/15 GGUF (opens in a new tab)
F16 19.6 GB 24.0 GB 43.1 tok/s Runs well 65 ptsGood (B) · 65 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

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.