AMD Radeon RX 7900 GRE
The AMD Radeon RX 7900 GRE has 16 GB VRAM and 576 GB/s memory bandwidth. It can run 36 of our 81 tracked models natively in VRAM at 8k context.
With 16 GB GDDR6, the AMD Radeon RX 7900 GRE is a consumer-tier GPU that can run 36 models natively. It handles 30B-class models at Q4 quantization.
AMD Radeon RX 7900 GRE: 2023 RDNA 3 with 16GB GDDR6 at 576 GB/s — a China/OEM-focused trim slotted between the RX 7900 XT and the RX 7800 XT.
7B-14B models fit natively at Q4. 27B models are tight or need CPU offload. ~7-11 t/s for 7B Q4.
ROCm Linux support with llama.cpp compiled for AMD. Windows users should use the Vulkan backend. Same 16GB-class model compatibility as the RTX 4060 Ti 16GB.
| Vendor | AMD |
| Architecture | RDNA 3 |
| VRAM | 16 GB |
| Memory type | GDDR6 |
| Memory bandwidth | 576 GB/s |
| Compute backend | ROCM |
| Tier | Consumer |
| Released | 2023 |
| Models (native) | 36 / 81 |
| Models (offload) | 13 / 81 |
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 (36)
- Qwen 3.5 35B-A3B (MoE)35B · MMLU-Pro 85.3Q2_K · ~94.1 t/s
- Nemotron 3 Nano 30B32B · MMLU-Pro 78.3Q2_K · ~88.2 t/s
- Qwen3 30B-A3B (MoE)30B · MMLU-Pro 61.5Q2_K · ~81.1 t/s
- Gemma 2 27B Instruct27.2B · MMLU-Pro 38.0Q2_K · ~27.8 t/s
- Gemma 3 27B Instruct27B · MMLU-Pro 67.5Q2_K · ~31.6 t/s
Show 31 more
- Qwen 3.6 27B27B · MMLU-Pro 86.2Q3_K_M · ~27.7 t/s
- Bonsai 27B27B · MMLU-Pro 81.5Ternary (Q2_0) · ~42.5 t/s
- Gemma 4 26B (MoE)26B · MMLU-Pro 82.6Q3_K_M · ~57.9 t/s
- Mistral Small 3.1 24B Instruct24B · MMLU-Pro 66.8Q3_K_M · ~29.1 t/s
- Mistral Small 22B22.2B · MMLU-Pro 49.2Q3_K_M · ~29.8 t/s
- GPT-OSS 20B21B · MMLU-Pro 67.9Q4_K_M · ~43.9 t/s
- Qwen3 14B14.8B · MMLU-Pro 61.0Q6_K · ~27.7 t/s
- Qwen 2.5 14B Instruct14.7B · MMLU-Pro 63.7Q5_K_M · ~31 t/s
- Phi-4 14B Instruct14B · MMLU-Pro 70.4Q6_K · ~29.2 t/s
- Mistral Nemo 12B Instruct12.2B · MMLU-Pro 35.6Q6_K · ~33 t/s
- Gemma 3 12B Instruct12.2B · MMLU-Pro 60.6Q6_K · ~33.8 t/s
- Gemma 4 12B (Unified)12B · MMLU-Pro 77.2Q6_K · ~28.6 t/s
- Gemma 2 9B Instruct9.2B · MMLU-Pro 32.0Q8_0 · ~29.7 t/s
- Llama 3.1 8B Instruct8B · MMLU-Pro 48.3Q8_0 · ~39.1 t/s
- DeepSeek R1 Distill Llama 8B8B · MMLU-Pro 41.0Q8_0 · ~39.1 t/s
- Qwen3 8B8B · MMLU-Pro 56.7Q8_0 · ~38.6 t/s
- Qwen 2.5 7B Instruct7.6B · MMLU-Pro 56.3Q8_0 · ~43.8 t/s
- Mistral 7B Instruct v0.37.25B · MMLU-Pro 30.0Q8_0 · ~42.6 t/s
- Gemma 3 4B Instruct4B · MMLU-Pro 43.6BF16 · ~44 t/s
- Gemma 4 E4B4B · MMLU-Pro 69.4BF16 · ~41.6 t/s
- Phi-3.5 Mini Instruct3.8B · MMLU-Pro 47.4BF16 · ~34.6 t/s
- Llama 3.2 3B Instruct3.2B · MMLU-Pro 24.0BF16 · ~51 t/s
- Qwen 2.5 3B Instruct3.1B · MMLU-Pro 32.4FP32 · ~29.5 t/s
- Gemma 2 2B Instruct2.6B · MMLU-Pro 17.8FP32 · ~33.2 t/s
- Gemma 4 E2B2B · MMLU-Pro 60.0FP32 · ~44.6 t/s
- SmolLM2 1.7B Instruct1.7B · MMLU-Pro 19.0FP32 · ~44.5 t/s
- Qwen 2.5 1.5B Instruct1.5B · MMLU-Pro 16.8FP32 · ~60 t/s
- Llama 3.2 1B Instruct1.24B · MMLU-Pro 12.5FP32 · ~71.6 t/s
- Gemma 3 1B Instruct1B · MMLU-Pro 14.7FP32 · ~86.5 t/s
- Qwen 2.5 0.5B Instruct0.5B · MMLU-Pro 10.0FP32 · ~178.2 t/s
- SmolLM2 360M Instruct0.36B · MMLU-Pro 8.0FP32 · ~210.9 t/s
Models that fit with CPU offload (13)
These use system RAM for layers that don't fit in VRAM — expect much slower inference.
- Qwen 2.5 72B Instruct72B · MMLU-Pro 71.1Q2_K · ~1.6 t/s
- Llama 3.3 70B Instruct70B · MMLU-Pro 68.9Q3_K_M · ~1.1 t/s
- DeepSeek R1 Distill Llama 70B70B · MMLU-Pro 70.0Q3_K_M · ~1.1 t/s
- Llama 3.1 70B Instruct70B · MMLU-Pro 66.4Q3_K_M · ~1.1 t/s
- Mixtral 8x7B Instruct v0.146.7B · MMLU-Pro 29.7Q5_K_M · ~1.3 t/s
- Command-R 35B35B · MMLU-Pro 33.0Q5_K_M · ~1.2 t/s
- Qwen 3.6 35B35B · MMLU-Pro 85.2Q6_K · ~1.5 t/s
- Yi 1.5 34B Chat34.4B · MMLU-Pro 37.0Q6_K · ~1.6 t/s
- Qwen3 32B32.8B · MMLU-Pro 65.5Q8_0 · ~1.1 t/s
- Qwen 2.5 32B Instruct32.5B · MMLU-Pro 69.0Q8_0 · ~1.1 t/s
- Qwen 2.5 Coder 32B Instruct32.5B · MMLU-Pro 50.4Q8_0 · ~1.1 t/s
- DeepSeek R1 Distill Qwen 32B32.5B · MMLU-Pro 65.0Q8_0 · ~1.1 t/s
- Gemma 4 31B31B · MMLU-Pro 85.2Q8_0 · ~1.1 t/s
Too large for this GPU (32)
- 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-4.5 Air 106B
- GLM-4.6 355B
- GLM-4.6V 106B
- 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
- Kimi K3
Continue reading
Frequently asked questions
- How much VRAM does the AMD Radeon RX 7900 GRE have?
- The AMD Radeon RX 7900 GRE has 16 GB of GDDR6 with 576 GB/s memory bandwidth.
- What is the AMD Radeon RX 7900 GRE best for?
- With 16 GB of VRAM, the AMD Radeon RX 7900 GRE handles smaller models (7B–14B) at Q4–Q5 quantization — ideal for entry-level local LLM experimentation and lightweight inference.
- What LLMs can the AMD Radeon RX 7900 GRE run locally?
- The AMD Radeon RX 7900 GRE can run 36 of the 81 open-weight models tracked by CanItRun natively in VRAM at 8k context. Top options include: Llama 3.1 8B Instruct at Q8_0, Llama 3.2 3B Instruct at BF16, Llama 3.2 1B Instruct at FP32.
- Can the AMD Radeon RX 7900 GRE run Llama 3.3 70B Instruct?
- The AMD Radeon RX 7900 GRE 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 GRE run Qwen 3.6 27B?
- Yes. The AMD Radeon RX 7900 GRE runs Qwen 3.6 27B natively in VRAM at Q3_K_M quantization, achieving approximately 27.7 tokens per second.
- Can the AMD Radeon RX 7900 GRE run Llama 3.1 8B Instruct?
- Yes. The AMD Radeon RX 7900 GRE runs Llama 3.1 8B Instruct natively in VRAM at Q8_0 quantization, achieving approximately 39.1 tokens per second.