Configure a rig →
Athene70B params8k context

Athene 70B locally

Athene 70B is an open-weight LLM from the Athene family with 70B parameters. Main use: chat, RAG and general assistance. Detected minimum hardware: Quadro RTX 8000 (48 GB).

Check on my GPU →Hugging Face ↗
Technical facts
Parameters70B
Max context8k
Q4_K_M44.0 GB
Q5_K_M53.8 GB
Q878.2 GB
FP16156.5 GB
FamilyAthene
Last sync2026-05-12

Available quantizations

Q4_K_M
44.0GB

Acceptable. Good compromise when VRAM is limited.

Q5_K_M
53.8GB

Good quality. Sweet spot for size and precision.

Q8
78.2GB

Near-FP16 quality. Comfortable for production.

FP16
156.5GB

Reference precision. Maximum quality, doubled VRAM.

Compatible GPUs

GPUs that can run Athene 70B on a single card, ranked by VRAM headroom.

Quadro RTX 8000
NVIDIA
48 GB · Quadro RTX
44.0 / 48 GBtight · Q4
RTX A6000
NVIDIA
48 GB · RTX A (Ampere)
44.0 / 48 GBtight · Q4
RTX 6000 Ada
NVIDIA
48 GB · RTX Ada
44.0 / 48 GBtight · Q4
NVIDIA A40
NVIDIA
48 GB · Ampere DC
44.0 / 48 GBtight · Q4
NVIDIA L40
NVIDIA
48 GB · Lovelace DC
44.0 / 48 GBtight · Q4
NVIDIA L40S
NVIDIA
48 GB · Lovelace DC
44.0 / 48 GBtight · Q4
Radeon Pro W7900
AMD
48 GB · Radeon Pro W
44.0 / 48 GBtight · Q4
Mac Mini M4 Pro (48GB)
Apple
48 GB · Mac Mini
44.0 / 48 GBtight · Q4
MacBook Pro 14 M4 Pro (48GB)
Apple
48 GB · MacBook Pro 14
44.0 / 48 GBtight · Q4
MacBook Pro 14 M4 Max (48GB)
Apple
48 GB · MacBook Pro 14
44.0 / 48 GBtight · Q4
MacBook Pro 16 M3 Max (48GB)
Apple
48 GB · MacBook Pro 16
44.0 / 48 GBtight · Q4
MacBook Pro 16 M4 Pro (48GB)
Apple
48 GB · MacBook Pro 16
44.0 / 48 GBtight · Q4

Recommended multi-GPU rigs

For Athene 70B at higher quantization or with more context, a multi-GPU rig gives more headroom.

4× RTX 2060 12GB
NVIDIA
48 GB · RTX 20
44.0 / 48 GBtight · Q4
2× TITAN RTX
NVIDIA
48 GB · RTX 20
44.0 / 48 GBtight · Q4
4× RTX 3060 12GB
NVIDIA
48 GB · RTX 30
44.0 / 48 GBtight · Q4
4× RTX 3080 12GB
NVIDIA
48 GB · RTX 30
44.0 / 48 GBtight · Q4
4× RTX 3080 Ti
NVIDIA
48 GB · RTX 30
44.0 / 48 GBtight · Q4
2× RTX 3090
NVIDIA
48 GB · RTX 30
44.0 / 48 GBtight · Q4
2× RTX 3090 Ti
NVIDIA
48 GB · RTX 30
44.0 / 48 GBtight · Q4
4× RTX 4070
NVIDIA
48 GB · RTX 40
44.0 / 48 GBtight · Q4

Recommended rig

4× RTX 2060 12GB

Athene 70B with Ubuntu, vLLM, Open WebUI and the model already downloaded.

Configure →

VRAM estimates: parameters x bits/8 plus margin. Real performance varies by engine, context length and batch size.
sync: 2026-05-12