Language

RX 460

CPU bottleneck check, compatible CPUs, and AI models it can run

Radeon RX 460 / AMD made / RX 500 / Released 2016 Also known as: RX460 / 460

Performance Score
3,500
VRAM
4GB
Power Draw (TDP)
75W
Manufacturer
AMD
Type
Desktop

Radeon RX 460 (AMD, released in 2016, also listed as RX460 / 460) is a graphics card with a performance score of 3,500 and 4GB of VRAM, TDP 75W. If CPU compatibility and performance balance are poor, a CPU bottleneck occurs, preventing RX 460 from reaching its full potential. In our estimate, the CPUs that pair best with RX 460 are Intel: Core i3-2120 (estimated bottleneck: about 0%), and AMD: AMD A6-7470K (about 0%). Below are the top 10 compatible CPUs, CPUs to avoid, and generative AI models supported by this amount of VRAM.

Top 10 CPUs Compatible with Radeon RX 460

CPUs are ordered by proximity to the ideal CPU:GPU ratio of 0.9:1. A lower bottleneck percentage means more of the GPU’s performance can be used.

3,200 pts
Bottleneck 0%
3,200 pts
Bottleneck 0%
3,200 pts
Bottleneck 0%
3,200 pts
Bottleneck 0%
3,300 pts
Bottleneck 0%
3,300 pts
Bottleneck 0%
3,500 pts
Bottleneck 0%
3,500 pts
Bottleneck 0%
3,500 pts
Bottleneck 0%
3,500 pts
Bottleneck 0%
Check Compatibility with Your CPU →

The Bottleneck Checker opens with Radeon RX 460 already selected.

RX 460 and CPU Compatibility | Where Does a CPU Bottleneck Begin?

RX 460 (RX460 / 460) has a performance score of 3,500 points. Using the same CPU:GPU ≈ 0.9:1 standard as the checker, compatibility by CPU score is shown below.

Example CPUs to PairRatingWhat It Means
AMD Phenom II X4 945、Core i3-3240、Core 2 Extreme QX9775 Great Match: 10% or Less Optimal balance. Nearly all of RX 460 performance can be used
AMD Athlon II X3 445、Core i3-540、AMD Phenom II X2 560 Acceptable: 10–25% Practical with no major issue. Consider a future upgrade if targeting high fps.
AMD Athlon II X2 260、Core 2 Quad Q9450、Core 2 Quad Q6700 CPU Too Weak: Over 25% A clear CPU bottleneck. Much of the GPU performance is wasted
Core i3-4170、Core i5-2300、Core i7-860 CPU Overkill Likely overkill for gaming

Note: Perceived results vary by resolution and game (GPU matters more at 4K, while CPU matters more at high-fps Full HD). For an exact estimate, use the Bottleneck Checker.

AI Models That Run on Radeon RX 460 (VRAM 4GB)

Runs Comfortably: Meets recommended VRAM / Barely Runs: Meets minimum VRAM (lower quality or quantization may be needed)

Image generation

Comfortable
SD 1.5 (Q4 quantized)
Image generation
GGUF Q4_K_M, ultra-lightweight
Minimum 2GB / Recommended 4GB
△ Barely
Stable Diffusion 1.5
Image generation
Basic image generation
Minimum 4GB / Recommended 6GB
△ Barely
SDXL (Q4 quantized)
Image generation
GGUF Q4_K_M, low VRAM
Minimum 4GB / Recommended 6GB
△ Barely
Real-ESRGAN x4
Image generation
Image upscaling (4x)
Minimum 4GB / Recommended 6GB

Large language models (LLM)

Comfortable
Qwen 2.5 0.5B (Q4)
Large language models (LLM)
Lightest model, for embedded devices
Minimum 1GB / Recommended 2GB
Comfortable
Qwen 2.5 1.5B (Q4)
Large language models (LLM)
Ultra-lightweight, runs on phones
Minimum 2GB / Recommended 3GB
Comfortable
Phi-3 mini 3.8B (Q4)
Large language models (LLM)
Small, high-performance model by Microsoft
Minimum 3GB / Recommended 4GB
Comfortable
Gemma 3 4B (Q4)
Large language models (LLM)
Lightweight model by Google
Minimum 3GB / Recommended 4GB
Comfortable
Llama 3.2 3B (Q4)
Large language models (LLM)
Small mobile model by Meta
Minimum 3GB / Recommended 4GB
Comfortable
Llama 3.2 1B (Q4)
Large language models (LLM)
Smallest mobile model by Meta
Minimum 2GB / Recommended 3GB
Comfortable
Mistral 7B (Q2)
Large language models (LLM)
Extreme quantization, quality trade-off
Minimum 3GB / Recommended 4GB
△ Barely
Gemma 4 E2B (Q4)
Large language models (LLM)
Google, April 2026, smallest phone-class model, accepts image and audio input
Minimum 4GB / Recommended 6GB
△ Barely
Qwen3.5 2B (Q4)
Large language models (LLM)
Alibaba, 2026, small multimodal model with thinking mode
Minimum 4GB / Recommended 6GB
△ Barely
MiniCPM5 2B (Q4)
Large language models (LLM)
OpenBMB, Sep 2026, small 2.5B model with long context and tool calling, Apache 2.0
Minimum 4GB / Recommended 6GB

Speech and music

Comfortable
Whisper Tiny
Speech and music
Ultra-lightweight speech recognition
Minimum 1GB / Recommended 2GB
Comfortable
Whisper Small
Speech and music
Lightweight speech recognition
Minimum 2GB / Recommended 3GB
Comfortable
Whisper Base
Speech and music
OpenAI, 74M, lightweight speech recognition
Minimum 1GB / Recommended 2GB
Comfortable
Kokoro-82M
Speech and music
82M ultra-lightweight TTS, multilingual including Japanese, practical on CPU
Minimum 1GB / Recommended 2GB
Comfortable
Parakeet TDT 0.6B v3
Speech and music
NVIDIA, 25 European languages, no Japanese support, very fast
Minimum 2GB / Recommended 4GB
Comfortable
Parakeet TDT-CTC 0.6B ja
Speech and music
NVIDIA, Japanese only, with punctuation, runs on NeMo
Minimum 2GB / Recommended 4GB
Comfortable
Style-Bert-VITS2 (JP-Extra)
Speech and music
A standard Japanese TTS, with emotion style control. Inference works on CPU, training needs 8GB or more
Minimum 2GB / Recommended 4GB
Comfortable
faster-whisper large-v3 (INT8)
Speech and music
Whisper on CTranslate2, faster and lighter on memory than the original
Minimum 3GB / Recommended 4GB
Comfortable
Granite Speech 5.0 470M
Speech and music
IBM, Aug 2026, lightweight 470M speech recognition, Apache 2.0
Minimum 3GB / Recommended 4GB
△ Barely
XTTS v2 (voice cloning)
Speech and music
Voice-cloning TTS
Minimum 4GB / Recommended 6GB
△ Barely
RVC (real-time voice conversion)
Speech and music
Voice conversion for streaming
Minimum 4GB / Recommended 8GB
△ Barely
kotoba-whisper v2.2
Speech and music
Kotoba Technologies, specialized for Japanese, about 6x faster than large-v3, with speaker separation and punctuation
Minimum 4GB / Recommended 6GB
△ Barely
Qwen3-ASR 0.6B
Speech and music
Alibaba, lightweight, for high-volume processing
Minimum 4GB / Recommended 6GB
△ Barely
GPT-SoVITS v2Pro
Speech and music
Clones a voice from 1 minute of audio, supports Japanese
Minimum 4GB / Recommended 6GB
△ Barely
Qwen3-TTS 0.6B
Speech and music
Alibaba, lightweight TTS, supports streaming
Minimum 4GB / Recommended 6GB
△ Barely
Irodori-TTS v4.1 Small
Speech and music
Japanese-only TTS, voice cloning, speaking style set with emoji, MIT
Minimum 4GB / Recommended 6GB
Models That Cannot Run (173)

Can You Explain These Specifications in Your Own Words?

Try teaching the AI “how to choose a CPU for Radeon RX 460.”
Putting your reasoning into words as if you were teaching someone sharpens your judgment when choosing parts. Start free, right here.

SciCirc — A free learning path for math, science, and computing through teaching AI →

Study Guide Route — Build a study order from your target school and current level →

Other GPUs in the Same Series

AMD Instinct MI300X AMD Instinct MI250X AMD Instinct MI210 AMD Instinct MI100 AMD Radeon Pro W7900 AMD Radeon Pro W7800 AMD Radeon Pro W6800 AMD Radeon Pro W6600 Radeon RX 9070 XT Radeon RX 9070 Radeon RX 9060 XT Radeon RX 7900 XTX

→ All GPUs / → Bottleneck Checker (Both Directions)

GPUs Commonly Compared with RX 460

RX 460 vs R9 270 RX 460 vs HD 6950 RX 460 vs HD 7850 RX 460 vs R7 370 RX 460 vs HD 6870 RX 460 vs RX 560

→ Compare Other Models / → Check Whether an Upgrade Is Worthwhile

Frequently Asked Questions About CPU Bottlenecks and Compatibility for RX 460

Which CPU minimizes the CPU bottleneck for RX 460(RX460 / 460)?

In our estimate, the best-balanced options are Core i3-2120 for Intel (estimated bottleneck: about 0%) and AMD A6-7470K for AMD (about 0%). A CPU-to-GPU performance ratio near 0.9:1 tends to use both parts effectively. See the top 10 compatible CPUs in the table on this page.

Which CPUs pair poorly with RX 460 and should be avoided?

As a guide, CPUs such as AMD Athlon II X2 260、Core 2 Quad Q9450、Core 2 Quad Q6700、Core 2 Duo E8600 push the bottleneck above 25% and waste much of the Radeon RX 460 performance. On the other hand, CPUs such as Core i3-4170、Core i5-2300、Core i7-860 are likely overkill for gaming.

How much VRAM does Radeon RX 460 have, and which generative AI models can it run?

Radeon RX 460 has 4GB of VRAM. It can comfortably run about 17 models, including Stable Diffusion and LLMs (for example, SD 1.5 (Q4 quantized), Qwen 2.5 0.5B (Q4), Qwen 2.5 1.5B (Q4)).

What is the power draw (TDP) of Radeon RX 460?

Radeon RX 460 has a power draw (TDP) of 75W. At 75W or less, many models can operate without a PCIe auxiliary power connector, making them suitable for PCs with limited power-supply headroom. Check the actual CPU pairing balance in the bottleneck diagnosis above.

Can Radeon RX 460 be used for both gaming and generative AI?

Its performance score is 3,500 points. CPU balance matters for gaming, while VRAM (4GB) matters for generative AI. Use the top 10 CPU list and AI model list above to check your use case.