Skip to content

CodeLlama 7B HF on RTX 5090: VRAM, speed and fit

CodeLlama 7B HF at 8-bit runs on the RTX 5090 with 16K of context at about 153 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on RTX 5090 · 8-bit (Q8_0) · Ollama / LM Studio · Chat

GPU memory
15.3 GB
of 32.0 GB
Context
16K
auto
Speed
153 tok/s
75 when full
First reply
0.1 s
2K prompt

Where the memory goes

Model
6.7 GB
Context
8.0 GB
Overhead
651 MB
OS
0.0 GB
Free
16.7 GB
Memory
15.3 GB of 32.0 GB
Context
16K tokens · auto
Speed
153 tok/s · 75 when full
First reply
0.1 s for a 2K prompt
Running cost
$9.30/mo at home · $29/mo on a cloud RTX 2000 Ada

Validation: Validated

What CodeLlama 7B HF on RTX 5090 was checked against
CheckTargetResultStatus
Fits in GPU memory32.0 GB usable15.3 GB neededPass
Headroom5% free16.7 GB free (52%)Pass
Context for chat16K or more16KPass
Writing speed15 tok/s or more153 tok/sPass
First replyunder 3 s, 2K prompt0.1 sPass

Targets: a reply you can read along with, a first reply the use case tolerates, and 5% of memory left free. Calculated from published specs, not benchmarked.

The setup

Model
CodeLlama 7B HF
Parameters
6.7B
Precision
8-bit (Q8_0)
Context
16K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
RTX 5090
GPU can use
32.0 GB of 32.0 GB

Running cost

At home
$9.30/mo
425 W at the wall
Renting instead
$29/mo
RTX 2000 Ada at $0.24/h

4 h a day, power at $0.18 per kWh, cloud at RunPod on-demand prices as of Nov 21, 2026.

How to run it

llama.cpp
llama-server -hf TheBloke/CodeLlama-7B-GGUF
vLLM
vllm serve codellama/CodeLlama-7b-hf
MLX (Mac)
mlx_lm.chat --model mlx-community/CodeLlama-7b-hf-4bit-mlx

CodeLlama 7B HF on similar machines

All machines: CodeLlama 7B HF VRAM requirements. Everything that runs here: what can the RTX 5090 run?

Other models that run on RTX 5090

Questions

Can CodeLlama 7B HF run on RTX 5090?

CodeLlama 7B HF at 8-bit runs on the RTX 5090 with 16K of context at about 153 tokens a second.

Report VR-024WS8R, calculated Nov 22, 2026 from published specs, not benchmarked.