What LLMs Can AMD Radeon RX 7900 XTX (24GB) Run?

Hardware capability guide for AMD Radeon RX 7900 XTX: 24GB memory with 960 GB/s bandwidth across single-card and multi-GPU deployments.

AMD Radeon RX 7900 XTX Hardware Specifications

VRAM / Card
24 GB
Mem Bandwidth
960 GB/s
FP16 Compute
61.4 TFLOPS
Architecture
RDNA 3
Release Year
2022
Available VRAM
24 GB
Total Bandwidth
960 GB/s
Fits FP16 / FP8
22
Fits w/ INT4
44 / 85
DeepSeek-R1-Distill-Qwen-32B
32B • DeepSeek
Fits INT4
FP16
68.27 GB
FP8
36 GB
INT4
19.86 GB
~44 tok/s (INT4)Open VRAM Calculator
DeepSeek-R1-Distill-Qwen-14B
14B • DeepSeek
Fits FP8+
FP16
32.27 GB
FP8
18 GB
INT4
10.86 GB
~22 tok/s (FP8)Open VRAM Calculator
DeepSeek-R1-Distill-Qwen-7B
7B • DeepSeek
Fits FP16+
FP16
18.27 GB
FP8
11 GB
INT4
7.36 GB
~11 tok/s (FP16)Open VRAM Calculator
DeepSeek-R1-Distill-Qwen-1.5B
1.5B • DeepSeek
Fits FP16+
FP16
7.27 GB
FP8
5.5 GB
INT4
4.61 GB
~11 tok/s (FP16)Open VRAM Calculator
DeepSeek-R1-Distill-Llama-8B
8B • DeepSeek
Fits FP16+
FP16
20.27 GB
FP8
12 GB
INT4
7.86 GB
~11 tok/s (FP16)Open VRAM Calculator
Llama 3 8B
8B • Llama 3
Fits FP16+
FP16
17.81 GB
FP8
9.31 GB
INT4
5.06 GB
~51 tok/s (FP16)Open VRAM Calculator
Llama 3.1 8B
8B • Llama 3
Fits FP16+
FP16
17.81 GB
FP8
9.31 GB
INT4
5.06 GB
~51 tok/s (FP16)Open VRAM Calculator
Llama 3.2 1B
1B • Llama 3
Fits FP16+
FP16
2.55 GB
FP8
1.43 GB
INT4
0.86 GB
~408 tok/s (FP16)Open VRAM Calculator
Llama 3.2 3B
3B • Llama 3
Fits FP16+
FP16
7.23 GB
FP8
3.79 GB
INT4
2.07 GB
~136 tok/s (FP16)Open VRAM Calculator
Llama 3.2 11B
11B • Llama 3
Fits FP8+
FP16
24.11 GB
FP8
12.61 GB
INT4
6.86 GB
~74 tok/s (FP8)Open VRAM Calculator
Qwen3.5-35B-A3BMoE 3B
35B • Qwen 3.5
Fits INT4
FP16
70.98 GB
FP8
35.66 GB
INT4
18.01 GB
~544 tok/s (INT4)Open VRAM Calculator
Qwen3.5-27B
27B • Qwen 3.5
Fits INT4
FP16
59.22 GB
FP8
30.97 GB
INT4
16.85 GB
~60 tok/s (INT4)Open VRAM Calculator
Qwen QwQ-32B
32B • Qwen QwQ
Fits INT4
FP16
69.1 GB
FP8
36.16 GB
INT4
19.69 GB
~51 tok/s (INT4)Open VRAM Calculator
Qwen2.5-Coder-32B
32B • Qwen 2
Fits INT4
FP16
69.1 GB
FP8
36.16 GB
INT4
19.69 GB
~51 tok/s (INT4)Open VRAM Calculator
Qwen3-32B
32B • Qwen 3
Fits INT4
FP16
69.23 GB
FP8
36.23 GB
INT4
19.73 GB
~51 tok/s (INT4)Open VRAM Calculator
Qwen2.5-32B
32B • Qwen 2
Fits INT4
FP16
69.1 GB
FP8
36.16 GB
INT4
19.69 GB
~51 tok/s (INT4)Open VRAM Calculator
Qwen2-32B
32B • Qwen 2
Fits INT4
FP16
69.1 GB
FP8
36.16 GB
INT4
19.69 GB
~51 tok/s (INT4)Open VRAM Calculator
Qwen3-30B-A3BMoE 3B
30B • Qwen 3
Fits INT4
FP16
61.1 GB
FP8
30.73 GB
INT4
15.54 GB
~544 tok/s (INT4)Open VRAM Calculator
Qwen2.5-14B
14B • Qwen 2
Fits FP8+
FP16
30.66 GB
FP8
16.04 GB
INT4
8.72 GB
~58 tok/s (FP8)Open VRAM Calculator
Qwen3-14B
14B • Qwen 3
Fits FP8+
FP16
30.66 GB
FP8
16.04 GB
INT4
8.72 GB
~58 tok/s (FP8)Open VRAM Calculator
Qwen2-14B
14B • Qwen 2
Fits FP8+
FP16
30.66 GB
FP8
16.04 GB
INT4
8.72 GB
~58 tok/s (FP8)Open VRAM Calculator
Qwen3-8B
8B • Qwen 3
Fits FP16+
FP16
17.93 GB
FP8
9.37 GB
INT4
5.09 GB
~51 tok/s (FP16)Open VRAM Calculator
Qwen2.5-7B
7B • Qwen 2
Fits FP16+
FP16
15.21 GB
FP8
7.96 GB
INT4
4.33 GB
~58 tok/s (FP16)Open VRAM Calculator
Qwen2-7B
7B • Qwen 2
Fits FP16+
FP16
15.21 GB
FP8
7.96 GB
INT4
4.33 GB
~58 tok/s (FP16)Open VRAM Calculator
Qwen3-4B
4B • Qwen 3
Fits FP16+
FP16
9 GB
FP8
4.72 GB
INT4
2.58 GB
~102 tok/s (FP16)Open VRAM Calculator
Qwen2.5-3B
3B • Qwen 2
Fits FP16+
FP16
6.57 GB
FP8
3.46 GB
INT4
1.91 GB
~136 tok/s (FP16)Open VRAM Calculator
Qwen2.5-1.5B
1.5B • Qwen 2
Fits FP16+
FP16
3.49 GB
FP8
1.89 GB
INT4
1.1 GB
~272 tok/s (FP16)Open VRAM Calculator
Qwen2.5-0.5B
0.5B • Qwen 2
Fits FP16+
FP16
1.36 GB
FP8
0.83 GB
INT4
0.57 GB
~816 tok/s (FP16)Open VRAM Calculator
Qwen3-0.6B
0.6B • Qwen 3
Fits FP16+
FP16
1.94 GB
FP8
1.12 GB
INT4
0.71 GB
~680 tok/s (FP16)Open VRAM Calculator
Qwen3-1.7B
1.7B • Qwen 3
Fits FP16+
FP16
4.14 GB
FP8
2.22 GB
INT4
1.26 GB
~240 tok/s (FP16)Open VRAM Calculator
Mistral-Nemo-12B
12B • Mistral
Fits FP8+
FP16
26.46 GB
FP8
13.83 GB
INT4
7.52 GB
~68 tok/s (FP8)Open VRAM Calculator
Mistral-7B-v0.3
7B • Mistral
Fits FP16+
FP16
15.71 GB
FP8
8.21 GB
INT4
4.46 GB
~58 tok/s (FP16)Open VRAM Calculator
Gemma-2-27B
27B • Gemma
Fits INT4
FP16
59.6 GB
FP8
31.16 GB
INT4
16.94 GB
~60 tok/s (INT4)Open VRAM Calculator
Gemma-2-9B
9B • Gemma
Fits FP16+
FP16
21.53 GB
FP8
11.22 GB
INT4
6.06 GB
~45 tok/s (FP16)Open VRAM Calculator
Gemma-2-2B
2B • Gemma
Fits FP16+
FP16
5.11 GB
FP8
2.71 GB
INT4
1.5 GB
~204 tok/s (FP16)Open VRAM Calculator
Phi-3.5-MoEMoE 6.6B
42B • Phi
Fits INT4
FP16
85.67 GB
FP8
43.17 GB
INT4
21.92 GB
~247 tok/s (INT4)Open VRAM Calculator
Phi-3-14B
14B • Phi
Fits FP8+
FP16
30.97 GB
FP8
16.19 GB
INT4
8.8 GB
~58 tok/s (FP8)Open VRAM Calculator
Phi-3-7B
7B • Phi
Fits FP16+
FP16
15.71 GB
FP8
8.21 GB
INT4
4.46 GB
~58 tok/s (FP16)Open VRAM Calculator
Phi-3-3.8B
3.8B • Phi
Fits FP16+
FP16
11.02 GB
FP8
5.72 GB
INT4
3.07 GB
~107 tok/s (FP16)Open VRAM Calculator
CodeLlama-34B
34B • CodeLlama
Fits INT4
FP16
72.93 GB
FP8
38.18 GB
INT4
20.8 GB
~48 tok/s (INT4)Open VRAM Calculator
CodeLlama-13B
13B • CodeLlama
Fits FP8+
FP16
33.56 GB
FP8
17.44 GB
INT4
9.37 GB
~63 tok/s (FP8)Open VRAM Calculator
CodeLlama-7B
7B • CodeLlama
Fits FP16+
FP16
18.71 GB
FP8
9.71 GB
INT4
5.21 GB
~58 tok/s (FP16)Open VRAM Calculator
GLM-4.7-FlashMoE 3B
30B • GLM-4
Fits INT4
FP16
66.1 GB
FP8
34.66 GB
INT4
18.94 GB
~51 tok/s (INT4)Open VRAM Calculator
GPT-OSS-20BMoE 3.6B
21B • GPT-OSS
Fits FP8+
FP16
43.15 GB
FP8
21.78 GB
INT4
11.09 GB
~227 tok/s (FP8)Open VRAM Calculator

AMD Radeon RX 7900 XTX 1x / 2x / 4x Multi-GPU LLM Compatibility Matrix

Precomputed at 8K context, batch size 1 across key benchmark models.

LLM ModelFP8 VRAM Req1× (24GB)2× (48GB)4× (96GB)
DeepSeek-R1(671B)675 GBNeeds 15×Needs 15×Needs 15×
DeepSeek-R1-Distill-Qwen-32B(32B)36 GBINT4FP8 / INT4FP16 / FP8 / INT4
Llama 4 Scout(109B)111.21 GBNeeds 3×Needs 3×INT4
Llama 3.1 8B(8B)9.31 GBFP16 / FP8 / INT4FP16 / FP8 / INT4FP16 / FP8 / INT4
Llama 3.1 70B(70B)78.31 GBNeeds 2×INT4FP8 / INT4
Qwen3-235B-A22B(235B)237.95 GBNeeds 6×Needs 6×Needs 6×
Qwen3-32B(32B)36.23 GBINT4FP8 / INT4FP16 / FP8 / INT4
Qwen3-14B(14B)16.04 GBFP8 / INT4FP16 / FP8 / INT4FP16 / FP8 / INT4
Mixtral-8x7B(46.7B)48.5 GBNeeds 2×INT4FP16 / FP8 / INT4
GPT-OSS-20B(21B)21.78 GBFP8 / INT4FP16 / FP8 / INT4FP16 / FP8 / INT4

Dedicated Compatibility Pages for All 22 GPUs

AMD Radeon RX 7900 XTX Local LLM Deployment FAQ

tools.gpuCompatibility.gpuDetail.faq.q1▾
With 24GB of memory on a single AMD Radeon RX 7900 XTX, 44 benchmark models in our registry fit cleanly in FP16, FP8, or INT4 at 8K context.
What generation speed can I expect from AMD Radeon RX 7900 XTX?▾
With 960 GB/s memory bandwidth and 24GB memory, single-stream decode speed scales inversely with active model weight size read per token.
When should I scale to 2x or 4x AMD Radeon RX 7900 XTX?▾
Multi-GPU tensor parallelism becomes necessary when model weights plus KV cache exceed 24GB or when serving high-concurrency batches.

Explore Related LLM & GPU Tools

Browse full AI toolkit directory →