AMD Radeon RX 6700, AI & Machine Learning Benchmarks & Specs

10GB · AI Score 1.6/100 · anchored estimate vs 51 measured cards

1.6 AI Score Includes estimates

We have not run AMD Radeon RX 6700 on our bench. These figures are anchored estimates, interpolated per workload against the 51 GPUs we did measure (confidence: low). On Llama 3.1 8B (Q4_K_M) AMD Radeon RX 6700 should deliver about 48.5 tokens/sec. Llama 3.3 70B does not fit. It needs roughly 42GB and this card has 10GB. 3 of the 12 workloads won't fit on 10GB at the tested precision, Qwen2.5-Coder 14B, Qwen3 32B, Llama 3.3 70B. We publish those as hard gates rather than quietly dropping to a smaller quant. Image, video and 3D models aren't listed for this card. They're built for NVIDIA's CUDA, and on AMD they only run through ROCm workarounds whose speed depends more on the driver and OS than on the card, so we don't estimate them, and they count as not supported in the AI score. For text generation (llama.cpp runs natively on ROCm and Vulkan), the numbers above hold up.

AI & Machine Learning benchmark results

Text Generation tok/s 8

WorkloadResultTelemetryData
Qwen3 4B78.5 tok/sestimatedEst.
Llama 3.1 8B48.5 tok/sestimatedEst.
Qwen2.5-Coder 14B✕ Won't fit needs ~12 GBVRAM-gated at this precisionEst.
Gemma 4 26B A4B✕ Won't fit needs ~20 GBVRAM-gated at this precisionEst.
Qwen3 30B A3B✕ Won't fit needs ~20 GBVRAM-gated at this precisionEst.
Gemma 4 31B✕ Won't fit needs ~22 GBVRAM-gated at this precisionEst.
Qwen3 32B✕ Won't fit VRAM-gated at this precisionEst.
Llama 3.3 70B✕ Won't fit VRAM-gated at this precisionEst.
How this estimate is derived. This card hasn’t been through our bench yet, so its numbers are anchored estimates, interpolated from the 51 first-party measured cards (Bandwidth Theil-Sen ladder off NVIDIA anchors × vendor factor (LLM ×0.85, diffusion ×0.5); realistic VRAM floors). The VRAM “won’t fit” gates are exact, since they’re pure capacity limits. Confidence: low. Estimates are replaced with measured data as more silicon goes through the bench. Full methodology →

AMD Radeon RX 6700 specifications

ArchitectureRDNA 2 (Navi 22)
Stream processors2,304
VRAM10GB GDDR6
Memory bus160-bit
Memory bandwidth320 GB/s
Boost clock2,450 MHz
TDP175 W
Process7nm
InterfacePCIe 4.0 x16
Release date2022-06-09
Launch MSRP$479

Verdict, capable, but 10GB sets the ceiling

AMD Radeon RX 6700 scores 1.6/100, #95 of 102. It ran 2 of 12; 3 exceeded its 10GB. Figures are anchored estimates, not measurements, we flag that on every row.

Relative performance: where the AMD Radeon RX 6700 lands

100% = this card, AI & Machine Learning headline metric (AI Score). #55 of 61 desktop cards in this vertical.

GPURelative%AI Score
NVIDIA GeForce RTX 5050
119%1.9
NVIDIA GeForce RTX 3050
113%1.8
NVIDIA GeForce GTX 1070 Ti
106%1.7
NVIDIA GeForce GTX 1080
106%1.7
AMD Radeon RX 6700
100%1.6
AMD Radeon RX 7600
100%1.6
NVIDIA GeForce GTX 1660 Super
100%1.6
NVIDIA GeForce GTX 1660 Ti
100%1.6
NVIDIA GeForce GTX 1660
94%1.5

Same card, other workloads: AMD Radeon RX 6700 Gaming benchmarks

← All AI & Machine Learning GPU rankings

The silicon

Transistors17,200 million
Die size335 mm²
Process node7 nm
Fabricated byTSMC
Transistor density51.3 million per mm²

Denser than 85% of the 746 cards we have silicon data for. Density is the clearest measure of what a process node bought: a card that gained it without growing the die got its speed from the fab rather than the architecture.

Silicon figures from Wikipedia (CC BY-SA 4.0). Benchmarks on this page are our own. Compare every chip.

What this card can build

Whole-job timings, composed from our measured per-model results on this card.

Can't run: Short social clips (needs Qwen3 32B), 60-second AI short film (needs Qwen3 32B), 24-frame storyboard (needs Qwen3 32B), 6-panel comic page (needs Qwen3 32B), Long-form article batch (needs Llama 3.3 70B), Full codebase review (needs Qwen2.5-Coder 14B).