AMD Radeon RX 7900 XTX
The AMD Radeon RX 7900 XTX has 24 GB VRAM and 960 GB/s memory bandwidth. It can run 44 of our 80 tracked models natively in VRAM at 8k context.
With 24 GB GDDR6, the AMD Radeon RX 7900 XTX is a consumer-tier GPU that can run 44 models natively. It handles 70B-class models at Q4 quantization.
The AMD Radeon RX 7900 XTX is the flagship RDNA 3 consumer GPU with 24GB GDDR6 at 960 GB/s. It matches the RTX 4090 on VRAM capacity at a significantly lower price point. ROCm support on Linux enables full GPU acceleration for llama.cpp and Ollama, making it the best value 24GB card for local LLM inference on an AMD platform.
AMD Radeon RX 7900 XTX: December 2022 RDNA 3 flagship with 24GB GDDR6 at 960 GB/s — AMD's consumer flagship.
7B-32B at Q4 native. ~8-15 t/s for 7B depending on backend.
ROCm Linux-only with llama.cpp compiled for AMD. Windows users need Vulkan driver. vLLM has strong MI300X support trickling down.
| Vendor | AMD |
| Architecture | RDNA 3 |
| VRAM | 24 GB |
| Memory type | GDDR6 |
| Memory bandwidth | 960 GB/s |
| Compute backend | ROCM |
| Tier | Consumer |
| Released | 2022 |
| Models (native) | 44 / 80 |
| Models (offload) | 7 / 80 |
Software: ROCm is Linux-only; on Windows use the Vulkan backend instead. Requires llama.cpp compiled with ROCm support.
Popular models for this GPU
Models this GPU runs natively in VRAM (44)
- Mixtral 8x7B Instruct v0.146.7B · MMLU-Pro 29.7Q2_K · ~35.7 t/s
- Qwen 3.5 35B-A3B (MoE)35B · MMLU-Pro 84.2Q3_K_M · ~111.1 t/s
- Qwen 3.6 35B35B · MMLU-Pro 85.2Q3_K_M · ~32.9 t/s
- Yi 1.5 34B Chat34.4B · MMLU-Pro 37.0Q3_K_M · ~33.6 t/s
- Qwen3 32B32.8B · MMLU-Pro 65.5Q3_K_M · ~36.5 t/s
- Qwen 2.5 32B Instruct32.5B · MMLU-Pro 69.0Q3_K_M · ~35.1 t/s
- Qwen 2.5 Coder 32B Instruct32.5B · MMLU-Pro 50.4Q3_K_M · ~35.1 t/s
- DeepSeek R1 Distill Qwen 32B32.5B · MMLU-Pro 65.0Q3_K_M · ~35.1 t/s
- Nemotron 3 Nano 30B32B · MMLU-Pro 78.3Q4_K_M · ~95.6 t/s
- Gemma 4 31B31B · MMLU-Pro 85.2Q3_K_M · ~34.4 t/s
- Qwen3 30B-A3B (MoE)30B · MMLU-Pro 61.5Q4_K_M · ~90.5 t/s
- Gemma 2 27B Instruct27.2B · MMLU-Pro 38.0Q4_K_M · ~31.8 t/s
- Gemma 3 27B Instruct27B · MMLU-Pro 67.5Q4_K_M · ~34.7 t/s
- Qwen 3.6 27B27B · MMLU-Pro 86.2Q4_K_M · ~34.6 t/s
- Bonsai 27B27B · MMLU-Pro 81.5Ternary (Q2_0) · ~70.8 t/s
- Gemma 4 26B (MoE)26B · MMLU-Pro 82.6Q5_K_M · ~59.8 t/s
- Mistral Small 3.1 24B Instruct24B · MMLU-Pro 66.8Q5_K_M · ~33.9 t/s
- Mistral Small 22B22.2B · MMLU-Pro 49.2Q6_K · ~31 t/s
- GPT-OSS 20B21B · MMLU-Pro 67.9Q6_K · ~55 t/s
- Qwen3 14B14.8B · MMLU-Pro 61.0Q8_0 · ~36.5 t/s
- Qwen 2.5 14B Instruct14.7B · MMLU-Pro 63.7Q8_0 · ~36.2 t/s
- Phi-4 14B Instruct14B · MMLU-Pro 70.4Q8_0 · ~38.5 t/s
- Mistral Nemo 12B Instruct12.2B · MMLU-Pro 35.6Q8_0 · ~43.6 t/s
- Gemma 3 12B Instruct12.2B · MMLU-Pro 60.6Q8_0 · ~44.5 t/s
- Gemma 4 12B (Unified)12B · MMLU-Pro 77.2Q8_0 · ~39.1 t/s
- Gemma 2 9B Instruct9.2B · MMLU-Pro 32.0Q8_0 · ~49.5 t/s
- Llama 3.1 8B Instruct8B · MMLU-Pro 48.3BF16 · ~36.5 t/s
- DeepSeek R1 Distill Llama 8B8B · MMLU-Pro 41.0BF16 · ~36.5 t/s
- Qwen3 8B8B · MMLU-Pro 56.7BF16 · ~36.3 t/s
- Qwen 2.5 7B Instruct7.6B · MMLU-Pro 56.3BF16 · ~39.8 t/s
- Mistral 7B Instruct v0.37.25B · MMLU-Pro 30.0BF16 · ~40.1 t/s
- Gemma 3 4B Instruct4B · MMLU-Pro 43.6FP32 · ~37.8 t/s
- Gemma 4 E4B4B · MMLU-Pro 69.4FP32 · ~36.7 t/s
- Phi-3.5 Mini Instruct3.8B · MMLU-Pro 47.4FP32 · ~33.9 t/s
- Llama 3.2 3B Instruct3.2B · MMLU-Pro 24.0FP32 · ~45.4 t/s
- Qwen 2.5 3B Instruct3.1B · MMLU-Pro 32.4FP32 · ~49.1 t/s
- Gemma 2 2B Instruct2.6B · MMLU-Pro 17.8FP32 · ~55.4 t/s
- Gemma 4 E2B2B · MMLU-Pro 60.0FP32 · ~74.3 t/s
- SmolLM2 1.7B Instruct1.7B · MMLU-Pro 19.0FP32 · ~74.2 t/s
- Qwen 2.5 1.5B Instruct1.5B · MMLU-Pro 16.8FP32 · ~100.1 t/s
- Llama 3.2 1B Instruct1.24B · MMLU-Pro 12.5FP32 · ~119.3 t/s
- Gemma 3 1B Instruct1B · MMLU-Pro 14.7FP32 · ~144.2 t/s
- Qwen 2.5 0.5B Instruct0.5B · MMLU-Pro 10.0FP32 · ~297 t/s
- SmolLM2 360M Instruct0.36B · MMLU-Pro 8.0FP32 · ~351.4 t/s
Models that fit with CPU offload (7)
These use system RAM for layers that don't fit in VRAM — expect much slower inference.
- GLM-4.5 Air 106B106B · MMLU-Pro 81.4Q2_K · ~3.1 t/s
- GLM-4.6V 106B106B · MMLU-Pro 79.9Q2_K · ~3.1 t/s
- Qwen 2.5 72B Instruct72B · MMLU-Pro 71.1Q3_K_M · ~1.6 t/s
- Llama 3.3 70B Instruct70B · MMLU-Pro 68.9Q3_K_M · ~1.7 t/s
- DeepSeek R1 Distill Llama 70B70B · MMLU-Pro 70.0Q3_K_M · ~1.7 t/s
- Llama 3.1 70B Instruct70B · MMLU-Pro 66.4Q3_K_M · ~1.7 t/s
- Command-R 35B35B · MMLU-Pro 33.0Q6_K · ~1.4 t/s
Too large for this GPU (29)
- Mixtral 8x22B Instruct v0.1
- Llama 3.1 405B Instruct
- DeepSeek V3 671B
- DeepSeek R1 671B
- Llama 4 Scout 109B
- Llama 4 Maverick 400B
- Qwen3 235B-A22B (MoE)
- MiniMax M1 456B
- GPT-OSS 120B
- GLM-4.5 355B
- GLM-4.6 355B
- GLM-4.7 358B
- Qwen 3.5 122B-A10B (MoE)
- MiniMax M2.5 229B
- GLM-5 744B
- MiniMax M2.7 229B
- Nemotron 3 Super 120B
- Kimi K2.6
- GLM-5.1 754B
- DeepSeek V4 Pro 1.6T
- DeepSeek V4 Flash 284B
- GLM-5.2 753B
- Nemotron 3 Ultra 550B-A55B
- Step 3.5 Flash
- Step 3.7 Flash
- MiMo V2.5 Pro
- Kimi K2.5
- MiniMax M3
- Inkling
Compare AMD Radeon RX 7900 XTX with other GPUs
Continue reading
hardware11 min
Best GPU for Running LLMs Locally in 2026comparisons9 min
GGUF vs EXL2 vs AWQ: Which Quantization Format to Usevram-guides9 min
Best LLMs for 24 GB VRAM (2026)hardware10 min
How to Choose Your First GPU for Local LLMstutorials12 min
llama.cpp Complete Setup Guide: Build, Configure, and Optimizetutorials9 min
How to Benchmark Your Local LLM Setupcomparisons10 min
Ollama vs LM Studio vs llama.cpp: Which Tool Should You Use?hardware9 min
Best GPUs $500-$1000 for LLMs (2026)hardware10 min
AMD Radeon for LLMs: ROCm & Vulkan Complete Guidetutorials11 min
Getting Started with Local LLMs (2026): The Complete Beginner's GuideFrequently asked questions
- How much VRAM does the AMD Radeon RX 7900 XTX have?
- The AMD Radeon RX 7900 XTX has 24 GB of GDDR6 with 960 GB/s memory bandwidth.
- What is the AMD Radeon RX 7900 XTX best for?
- With 24 GB of VRAM, the AMD Radeon RX 7900 XTX is well-suited for running 7B–32B models at Q4 with room for context, making it a great all-rounder for local LLM inference.
- What LLMs can the AMD Radeon RX 7900 XTX run locally?
- The AMD Radeon RX 7900 XTX can run 44 of the 80 open-weight models tracked by CanItRun natively in VRAM at 8k context. Top options include: Llama 3.1 8B Instruct at BF16, Llama 3.2 3B Instruct at FP32, Llama 3.2 1B Instruct at FP32.
- Can the AMD Radeon RX 7900 XTX run Llama 3.3 70B Instruct?
- The AMD Radeon RX 7900 XTX can run Llama 3.3 70B Instruct with CPU offload at Q3_K_M quantization, but inference will be slower than native VRAM execution.
- Can the AMD Radeon RX 7900 XTX run Qwen 3.6 27B?
- Yes. The AMD Radeon RX 7900 XTX runs Qwen 3.6 27B natively in VRAM at Q4_K_M quantization, achieving approximately 34.6 tokens per second.
- Can the AMD Radeon RX 7900 XTX run Llama 3.1 8B Instruct?
- Yes. The AMD Radeon RX 7900 XTX runs Llama 3.1 8B Instruct natively in VRAM at BF16 quantization, achieving approximately 36.5 tokens per second.