# Llama 3.1 8B Instruct (Q4_K_M)

> Meta · 8B · q4_k_m

Canonical: https://gpuninja.com/models/llama-3-1-8b-instruct-q4-k-m
Data as of: 2026-10-11T15:48:18Z
Path: Home › AI models
- Specs verified: 11 Oct 2026, 15:48 UTC

## Specifications

- Publisher: Meta (Verified · source github.com · retrieved 11 Oct 2026, 15:42 UTC · checked 11 Oct 2026, 15:48 UTC)
- Parameters: 8B (Verified · source huggingface.co · retrieved 11 Oct 2026, 15:40 UTC · checked 11 Oct 2026, 15:48 UTC)
- Quantization: q4_k_m (Verified · source huggingface.co · retrieved 11 Oct 2026, 15:40 UTC · checked 11 Oct 2026, 15:48 UTC)
- Minimum VRAM: 4.9 GB (Unverified · source huggingface.co · retrieved 11 Oct 2026, 15:40 UTC · checked 11 Oct 2026, 15:48 UTC)
- Context length: 128K tokens (Verified · source huggingface.co · retrieved 11 Oct 2026, 15:40 UTC · checked 11 Oct 2026, 15:48 UTC)
- Modality: text (Verified · source github.com · retrieved 11 Oct 2026, 15:42 UTC · checked 11 Oct 2026, 15:48 UTC)
- License: Llama 3.1 Community License (Verified · source github.com · retrieved 11 Oct 2026, 15:42 UTC · checked 11 Oct 2026, 15:48 UTC)

## Graphics cards that can run it

Board, Chip, VRAM, TDP, Length, Slots, Price, Stock, VRAM headroom

- GeForce RTX 4060 Ti Founders Edition — [GeForce RTX 4060 Ti](https://gpuninja.com/chips/geforce-rtx-4060-ti), 8 GB, 160 W, 244 mm, 2-slot, Not recorded, Last recorded out of stock, Discontinued — 3.1 GB spare
- [PRIME GeForce RTX 5070 OC Edition](https://gpuninja.com/boards/asus-prime-5070-oc) — [GeForce RTX 5070](https://gpuninja.com/chips/geforce-rtx-5070), 12 GB, 250 W, 304 mm, 2.5-slot, Not recorded, No listings — 7.1 GB spare
- [Arc B580 Limited Edition](https://gpuninja.com/boards/intel-b580-limited-edition) — [Arc B580](https://gpuninja.com/chips/arc-b580), 12 GB, 190 W, 272 mm, 2-slot, Not recorded, No listings — 7.1 GB spare
- [GeForce RTX 4070 SUPER 12G VENTUS 2X OC](https://gpuninja.com/boards/msi-ventus-2x-4070-super-oc) — [GeForce RTX 4070 SUPER](https://gpuninja.com/chips/geforce-rtx-4070-super), 12 GB, 220 W, 242 mm, 2.1-slot, Not recorded, No listings — 7.1 GB spare
- [GeForce RTX 5070 12G VENTUS 2X OC](https://gpuninja.com/boards/msi-ventus-2x-5070-oc) — [GeForce RTX 5070](https://gpuninja.com/chips/geforce-rtx-5070), 12 GB, 250 W, 236 mm, 2.5-slot, Not recorded, No listings — 7.1 GB spare
- GeForce RTX 4070 SUPER Founders Edition — [GeForce RTX 4070 SUPER](https://gpuninja.com/chips/geforce-rtx-4070-super), 12 GB, 220 W, 244 mm, 2-slot, Not recorded, Last recorded out of stock, Discontinued — 7.1 GB spare
- [GeForce RTX 5070 Founders Edition](https://gpuninja.com/boards/nvidia-5070-founders-edition) — [GeForce RTX 5070](https://gpuninja.com/chips/geforce-rtx-5070), 12 GB, 250 W, 242 mm, 2-slot, Not recorded, No listings — 7.1 GB spare
- [Radeon RX 9070 XT Taichi 16GB OC](https://gpuninja.com/boards/asrock-taichi-9070-xt-oc) — [Radeon RX 9070 XT](https://gpuninja.com/chips/radeon-rx-9070-xt), 16 GB, 340 W, 330 mm, 3-slot, Not recorded, No listings — 11.1 GB spare
- [Prime Radeon RX 9070 XT OC Edition](https://gpuninja.com/boards/asus-prime-9070-xt-oc) — [Radeon RX 9070 XT](https://gpuninja.com/chips/radeon-rx-9070-xt), 16 GB, 317 W, 312 mm, 2.5-slot, Not recorded, No listings — 11.1 GB spare
- [ProArt GeForce RTX 4080 SUPER](https://gpuninja.com/boards/asus-proart-4080-super) — [GeForce RTX 4080 SUPER](https://gpuninja.com/chips/geforce-rtx-4080-super), 16 GB, 320 W, 300 mm, 2.5-slot, Not recorded, No listings — 11.1 GB spare
- [TUF Gaming GeForce RTX 5070 Ti OC Edition](https://gpuninja.com/boards/asus-tuf-gaming-5070-ti-oc) — [GeForce RTX 5070 Ti](https://gpuninja.com/chips/geforce-rtx-5070-ti), 16 GB, 300 W, 329 mm, 3.1-slot, Not recorded, No listings — 11.1 GB spare
- [TUF Gaming GeForce RTX 5080 OC Edition](https://gpuninja.com/boards/asus-tuf-gaming-5080-oc) — [GeForce RTX 5080](https://gpuninja.com/chips/geforce-rtx-5080), 16 GB, 360 W, 348 mm, 3.6-slot, Not recorded, No listings — 11.1 GB spare
- [TUF Gaming Radeon RX 9070 XT OC Edition](https://gpuninja.com/boards/asus-tuf-gaming-9070-xt-oc) — [Radeon RX 9070 XT](https://gpuninja.com/chips/radeon-rx-9070-xt), 16 GB, 332 W, 330 mm, 3.1-slot, Not recorded, No listings — 11.1 GB spare
- [Radeon RX 9070 XT GAMING OC 16G](https://gpuninja.com/boards/gigabyte-gaming-9070-xt-oc) — [Radeon RX 9070 XT](https://gpuninja.com/chips/radeon-rx-9070-xt), 16 GB, 330 W, 288 mm, 2.8-slot, Not recorded, No listings — 11.1 GB spare
- [GeForce RTX 5080 16G GAMING TRIO OC](https://gpuninja.com/boards/msi-gaming-trio-5080-oc) — [GeForce RTX 5080](https://gpuninja.com/chips/geforce-rtx-5080), 16 GB, 360 W, 338 mm, 2.5-slot, Not recorded, No listings — 11.1 GB spare
- [GeForce RTX 5060 Ti 16G VENTUS 2X OC PLUS](https://gpuninja.com/boards/msi-ventus-2x-5060-ti-16-gb-oc-plus) — [GeForce RTX 5060 Ti](https://gpuninja.com/chips/geforce-rtx-5060-ti), 16 GB, 180 W, 227 mm, 2-slot, Not recorded, No listings — 11.1 GB spare
- [GeForce RTX 5070 Ti 16G VENTUS 3X OC](https://gpuninja.com/boards/msi-ventus-3x-5070-ti-oc) — [GeForce RTX 5070 Ti](https://gpuninja.com/chips/geforce-rtx-5070-ti), 16 GB, 300 W, 303 mm, 2.4-slot, Not recorded, No listings — 11.1 GB spare
- GeForce RTX 4080 SUPER Founders Edition — [GeForce RTX 4080 SUPER](https://gpuninja.com/chips/geforce-rtx-4080-super), 16 GB, 320 W, 304 mm, 3-slot, Not recorded, Last recorded out of stock, Discontinued — 11.1 GB spare
- [GeForce RTX 5080 Founders Edition](https://gpuninja.com/boards/nvidia-5080-founders-edition) — [GeForce RTX 5080](https://gpuninja.com/chips/geforce-rtx-5080), 16 GB, 360 W, 304 mm, 2-slot, Not recorded, No listings — 11.1 GB spare
- [Hellhound AMD Radeon RX 9070 XT 16GB GDDR6](https://gpuninja.com/boards/powercolor-hellhound-9070-xt) — [Radeon RX 9070 XT](https://gpuninja.com/chips/radeon-rx-9070-xt), 16 GB, 317 W, 340 mm, 2.5-slot, Not recorded, No listings — 11.1 GB spare
- [Reaper AMD Radeon RX 9070 XT 16GB GDDR6](https://gpuninja.com/boards/powercolor-reaper-9070-xt) — [Radeon RX 9070 XT](https://gpuninja.com/chips/radeon-rx-9070-xt), 16 GB, 304 W, 304 mm, 2-slot, Not recorded, No listings — 11.1 GB spare
- [Red Devil AMD Radeon RX 9070 XT 16GB GDDR6](https://gpuninja.com/boards/powercolor-red-devil-9070-xt) — [Radeon RX 9070 XT](https://gpuninja.com/chips/radeon-rx-9070-xt), 16 GB, 330 W, 352 mm, 3-slot, Not recorded, No listings — 11.1 GB spare
- [NITRO+ AMD Radeon RX 9070 XT OC](https://gpuninja.com/boards/sapphire-nitro-9070-xt-oc) — [Radeon RX 9070 XT](https://gpuninja.com/chips/radeon-rx-9070-xt), 16 GB, 330 W, 330.8 mm, 3.2-slot, Not recorded, No listings — 11.1 GB spare
- [PULSE AMD Radeon RX 7800 XT 16GB](https://gpuninja.com/boards/sapphire-pulse-7800-xt) — [Radeon RX 7800 XT](https://gpuninja.com/chips/radeon-rx-7800-xt), 16 GB, 266 W, 280 mm, 2.5-slot, Not recorded, No listings — 11.1 GB spare
- [PULSE AMD Radeon RX 9060 XT OC 16GB](https://gpuninja.com/boards/sapphire-pulse-9060-xt-16-gb-oc) — [Radeon RX 9060 XT 16 GB](https://gpuninja.com/chips/radeon-rx-9060-xt-16-gb), 16 GB, 170 W, 240 mm, 2.3-slot, Not recorded, No listings — 11.1 GB spare
- [PULSE AMD Radeon RX 9070](https://gpuninja.com/boards/sapphire-pulse-9070) — [Radeon RX 9070](https://gpuninja.com/chips/radeon-rx-9070), 16 GB, 220 W, 280 mm, 2.5-slot, Not recorded, No listings — 11.1 GB spare
- [PULSE AMD Radeon RX 9070 XT](https://gpuninja.com/boards/sapphire-pulse-9070-xt) — [Radeon RX 9070 XT](https://gpuninja.com/chips/radeon-rx-9070-xt), 16 GB, 304 W, 320 mm, 3-slot, Not recorded, No listings — 11.1 GB spare
- [PURE AMD Radeon RX 9070 XT OC](https://gpuninja.com/boards/sapphire-pure-9070-xt-oc) — [Radeon RX 9070 XT](https://gpuninja.com/chips/radeon-rx-9070-xt), 16 GB, 317 W, 320 mm, 3-slot, Not recorded, No listings — 11.1 GB spare
- [Mercury AMD Radeon RX 9070XT OC Magnetic Air Edition with RGB](https://gpuninja.com/boards/xfx-mercury-9070-xt-oc-magnetic-air) — [Radeon RX 9070 XT](https://gpuninja.com/chips/radeon-rx-9070-xt), 16 GB, 340 W, 360 mm, 3.5-slot, Not recorded, No listings — 11.1 GB spare
- [Swift AMD Radeon RX 9070XT Triple Fan Gaming Edition](https://gpuninja.com/boards/xfx-swift-9070-xt) — [Radeon RX 9070 XT](https://gpuninja.com/chips/radeon-rx-9070-xt), 16 GB, 304 W, 325 mm, 3.5-slot, Not recorded, No listings — 11.1 GB spare
- [ROG Strix GeForce RTX 4090](https://gpuninja.com/boards/asus-rog-strix-4090) — [GeForce RTX 4090](https://gpuninja.com/chips/geforce-rtx-4090), 24 GB, 450 W, 357.6 mm, 3.5-slot, Not recorded, No listings — 19.1 GB spare
- [ROG Strix GeForce RTX 4090 OC Edition](https://gpuninja.com/boards/asus-rog-strix-4090-oc) — [GeForce RTX 4090](https://gpuninja.com/chips/geforce-rtx-4090), 24 GB, 500 W, 357.6 mm, 3.5-slot, Not recorded, No listings — 19.1 GB spare
- [TUF Gaming GeForce RTX 4090 OC Edition](https://gpuninja.com/boards/asus-tuf-gaming-4090-oc) — [GeForce RTX 4090](https://gpuninja.com/chips/geforce-rtx-4090), 24 GB, 450 W, 348.2 mm, 3.7-slot, Not recorded, No listings — 19.1 GB spare
- [GeForce RTX 4090 GAMING OC 24G](https://gpuninja.com/boards/gigabyte-gaming-4090-oc) — [GeForce RTX 4090](https://gpuninja.com/chips/geforce-rtx-4090), 24 GB, 450 W, 340 mm, 3.7-slot, Not recorded, No listings — 19.1 GB spare
- [GeForce RTX 4090 GAMING X TRIO 24G](https://gpuninja.com/boards/msi-gaming-x-trio-4090) — [GeForce RTX 4090](https://gpuninja.com/chips/geforce-rtx-4090), 24 GB, 450 W, 337 mm, 3.8-slot, Not recorded, No listings — 19.1 GB spare
- [GeForce RTX 4090 SUPRIM X 24G](https://gpuninja.com/boards/msi-suprim-x-4090) — [GeForce RTX 4090](https://gpuninja.com/chips/geforce-rtx-4090), 24 GB, 480 W, 336 mm, 3.8-slot, Not recorded, No listings — 19.1 GB spare
- GeForce RTX 4090 Founders Edition — [GeForce RTX 4090](https://gpuninja.com/chips/geforce-rtx-4090), 24 GB, 450 W, 304 mm, 3-slot, Not recorded, Last recorded out of stock, Discontinued — 19.1 GB spare
- [NITRO+ AMD Radeon RX 7900 XTX Vapor-X 24GB](https://gpuninja.com/boards/sapphire-nitro-7900-xtx-vapor-x) — [Radeon RX 7900 XTX](https://gpuninja.com/chips/radeon-rx-7900-xtx), 24 GB, 420 W, 320 mm, 3.5-slot, Not recorded, No listings — 19.1 GB spare
- [PULSE AMD Radeon RX 7900 XTX 24GB](https://gpuninja.com/boards/sapphire-pulse-7900-xtx) — [Radeon RX 7900 XTX](https://gpuninja.com/chips/radeon-rx-7900-xtx), 24 GB, 370 W, 313 mm, 2.7-slot, Not recorded, No listings — 19.1 GB spare
- [ROG Astral GeForce RTX 5090 OC Edition](https://gpuninja.com/boards/asus-rog-astral-5090-oc) — [GeForce RTX 5090](https://gpuninja.com/chips/geforce-rtx-5090), 32 GB, 600 W, 357.6 mm, 3.8-slot, Not recorded, No listings — 27.1 GB spare
- [GeForce RTX 5090 32G GAMING TRIO OC](https://gpuninja.com/boards/msi-gaming-trio-5090-oc) — [GeForce RTX 5090](https://gpuninja.com/chips/geforce-rtx-5090), 32 GB, 575 W, 359 mm, 3.4-slot, Not recorded, No listings — 27.1 GB spare
- [GeForce RTX 5090 Founders Edition](https://gpuninja.com/boards/nvidia-5090-founders-edition) — [GeForce RTX 5090](https://gpuninja.com/chips/geforce-rtx-5090), 32 GB, 575 W, 304 mm, 2-slot, Not recorded, No listings — 27.1 GB spare

## Benchmarks

No benchmark results recorded.

## Sources

- https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/MODEL_CARD.md — Publisher, Modality, License; last verified 11 Oct 2026, 15:48 UTC
- https://huggingface.co/unsloth/Llama-3.1-8B-Instruct — Parameters; last verified 11 Oct 2026, 15:48 UTC
- https://huggingface.co/bartowski/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf — Quantization, Minimum VRAM; last verified 11 Oct 2026, 15:48 UTC
- https://huggingface.co/unsloth/Llama-3.1-8B-Instruct/blob/main/config.json — Context length; last verified 11 Oct 2026, 15:48 UTC