RUNLOCALAIv38
→WILL IT RUNBEST GPUCOMPARETROUBLESHOOTSTARTPULSEMODELSHARDWARETOOLSBENCH
RUNLOCALAI

Operator-grade instrument for local-AI hardware intelligence. Hand-written verdicts. Real benchmarks. Reproducible commands.

OP·Fredoline Eruo
DIR
  • Models
  • Hardware
  • Tools
  • Benchmarks
  • Will it run?
GUIDES
  • Best GPU
  • Best laptop
  • Best Mac
  • Best used GPU
  • Best budget GPU
  • Best GPU for Ollama
  • Best GPU for SD
  • AI PC build $2K
  • CUDA vs ROCm
  • 16 vs 24 GB
  • Compare hardware
  • Custom compare
REF
  • Systems
  • Ecosystem maps
  • Pillar guides
  • Methodology
  • Glossary
  • Errors KB
  • Troubleshooting
  • Resources
  • Public API
EDITOR
  • About
  • About the author
  • Changelog
  • Latest
  • Updates
  • Submit benchmark
  • Send feedback
  • Trust
  • Editorial policy
  • How we make money
  • Contact
LEGAL
  • Privacy
  • Terms
  • Sitemap
MAIL · MONTHLY DIGEST
Get monthly local AI changes
Monthly recap. No spam.
DISCLOSURE

Some links on this site are affiliate links (Amazon Associates and other first-class retailers). When you buy through them, we earn a small commission at no extra cost to you. Affiliate links do not influence our verdicts — there are cards we rate highly that we don't have affiliate relationships with, and cards that sell well that we refuse to recommend. Read more →

SYS · ONLINEUPTIME · 100%2026 · operator-owned
RUNLOCALAI · v38
  1. >
  2. Home
  3. /Hardware
  4. /AMD Radeon RX 6700 XT
UNIT · AMD · GPU
12 GB VRAMhigh·Reviewed May 2026

AMD Radeon RX 6700 XT

12 GB RDNA 2 at the $280 used tier. ROCm officially supported. The VRAM headroom matters — fits 13B Q4 comfortably. ~50-65 tok/s on 7B Q4. Strong AMD value pick for the 'more VRAM than NVIDIA at this price' decision shape.

Released 2021·~$280 street·384 GB/s memory bandwidth
RUNLOCALAI SCORE
See full leaderboard →
255/ 1000
DD-tier
Estimated
Throughput
111/ 500
VRAM-fit
110/ 200
Ecosystem
130/ 200
Efficiency
13/ 100

Extrapolated from 384 GB/s bandwidth — 38.4 tok/s estimated. No measured benchmarks yet.

WORKLOAD FIT
Try other hardware →

Plain-English: Comfortable at 14B and below — coding agent feels deliberate.

7B chat✓
Comfortable
14B chat✓
Comfortable
32B chat✗
Doesn't fit
70B chat✗
Doesn't fit
Coding agent~
Tight
Vision (≤8B VLM)~
Tight
Long context (32K)~
Tight
✓Comfortable — fits with headroom
~Tight — works, no slack
△Marginal — needs aggressive quant
✗Doesn't fit usefully

Verdicts extrapolated from catalog VRAM + bandwidth + ecosystem flags. Hover any chip for the rationale. Want measured numbers? Submit your own run with runlocalai-bench --submit.

BLK · VERDICT

Our verdict

OP · Fredoline Eruo|VERIFIED MAY 10, 2026
6.8/10

The RX 6700 XT is for the operator who needs 12 GB VRAM at a sub-$300 used price and is willing to work within ROCm's software ecosystem. It fits 13B Q4 comfortably and runs 7B Q4 at an estimated 42-60 tok/s, making it a solid mid-range inference card. The 384 GB/s bandwidth also handles 30B Q4 models at ~15-20 tok/s, but 70B models are out of reach. ROCm support is official, but PyTorch and vLLM integration can be less polished than CUDA, and some inference frameworks may lack full optimization. Pass on this card if the workload requires 70B models, needs CUDA-exclusive features, or demands the plug-and-play experience of NVIDIA cards. At $280 used, this is a strong AMD value pick for the 'more VRAM than NVIDIA at this price' decision shape.

›Why this rating

The 12 GB VRAM at $280 is a compelling value for local AI inference, especially for 13B models. However, the ROCm software stack and lower bandwidth compared to similarly priced used NVIDIA cards (e.g., RTX 3060 12GB) limit its versatility and peak performance.

BLK · OVERVIEW

Overview

12 GB RDNA 2 at the $280 used tier. ROCm officially supported. The VRAM headroom matters — fits 13B Q4 comfortably. ~50-65 tok/s on 7B Q4. Strong AMD value pick for the 'more VRAM than NVIDIA at this price' decision shape.

Retailers we'd check:Amazon

Search-fallback links. Editorial hasn't yet curated retailer URLs for this card. Approx. $280.

Some links above are affiliate links. We may earn a commission at no extra cost to you. How we make money.

BLK · SPECS

Specs

VRAM12 GB
Power draw230 W
Released2021
MSRP$479
Backends
ROCm
Vulkan

Models that fit

Open-weight models small enough to run on AMD Radeon RX 6700 XT with usable context.

Llama 3.2 3B Instruct
3B · llama
Qwen 2.5 7B Instruct
7B · qwen
DeepSeek R1 Distill Qwen 7B
7B · deepseek
Gemma 4 E4B (Effective 4B)
4B · gemma
Qwen 3 4B
4B · qwen
Phi-3.5 Mini Instruct
3.8B · phi
Llama 3.2 1B Instruct
1B · llama
Gemma 3 4B
4B · gemma

Frequently asked

What models can AMD Radeon RX 6700 XT run?

With 12GB VRAM, the AMD Radeon RX 6700 XT runs models up to 14B in 4-bit, or 7B at higher quantizations. See the model list below for tested combinations.

Does AMD Radeon RX 6700 XT support CUDA?

No — AMD Radeon RX 6700 XT is an AMD card. Use ROCm (Linux) or the Vulkan backend in llama.cpp instead. CUDA-only tools won't work.

How much does AMD Radeon RX 6700 XT cost?

Current street price for AMD Radeon RX 6700 XT is around $280 (MSRP $479). Prices vary by region and supply.

Where next?

Buyer guides
  • Best GPU for local AI →
  • Best laptop for local AI →
  • Best Mac for local AI →
  • Best used GPU for local AI →
Troubleshooting
  • CUDA out of memory →
  • Ollama running slowly →
  • ROCm not detected →
  • Model keeps crashing →

Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify hardware specifications.

Compare alternatives

Hardware worth comparing

Same VRAM tier and the one step above and below — so you can frame the buying decision against real options.

Same VRAM tier
Cards in the same memory band
  • NVIDIA GeForce RTX 2070 Super
    nvidia · 8 GB VRAM
    4.8/10
  • NVIDIA GeForce RTX 3060 Ti
    nvidia · 8 GB VRAM
    5.0/10
  • NVIDIA GeForce RTX 3060 12GB
    nvidia · 12 GB VRAM
    7.0/10
  • NVIDIA GeForce RTX 2080 Super
    nvidia · 8 GB VRAM
    5.1/10
  • AMD Radeon RX 6750 XT
    amd · 12 GB VRAM
    7.1/10
  • Intel Arc A770 16GB
    intel · 16 GB VRAM
    6.5/10
Step up
More VRAM — bigger models, more context
  • AMD Radeon RX 6800
    amd · 16 GB VRAM
    7.3/10
  • NVIDIA GeForce RTX 2080 Ti
    nvidia · 11 GB VRAM
    6.6/10
  • Intel Arc A770 16GB
    intel · 16 GB VRAM
    6.5/10
Step down
Less VRAM — cheaper, more constrained
  • NVIDIA GeForce RTX 2070 Super
    nvidia · 8 GB VRAM
    4.8/10
  • AMD Radeon RX 5700 XT
    amd · 8 GB VRAM
    3.5/10
  • Intel Arc A770 16GB
    intel · 16 GB VRAM
    6.5/10