AMD RX 7700 XT (12GB)
The AMD RX 7700 XT (12GB) provides 12 GB of memory with 432 GB/s bandwidth, supporting local inference via ROCm and Vulkan acceleration.
Memory
12 GB
Usable Memory Ceiling
12 GB
Bandwidth
432 GB/s
Max Inference Class
14B Models (Q4)
TDP
245W
VRAM Scaling by Context Length
Estimated memory requirements as context length increases. Curves crossing above the reference line indicate Out of Memory (OOM).
Precision:
Best Models to Run on AMD RX 7700 XT (12GB)
Inference throughput, memory compatibility, and generation speeds for open-weights LLMs on AMD RX 7700 XT (12GB).
Sort by:
Context:
KV Cache:
GPUs:
| Rank | Model | Parameters | Precision | TPS (Approx.) | TTFT | Can Run |
|---|---|---|---|---|---|---|
#112 | Phi-4 Reasoning Plus | 14B | INT4 | 26 tok/s | ~3.0s | |
#125 | Qwen3.5-9B | 9B | INT4 Q8 | 56 tok/s 33 tok/s | ~1.6s ~1.8s | |
#128 | K2 Horizon 7B | 7B | INT4 Q8 | 68 tok/s 43 tok/s | ~1.3s ~1.3s | |
#135 | Gemma 4 12B | 11.95B | INT4 | 31 tok/s | ~2.4s | |
#140 | Qwen3.5-4B | 4B | INT4 Q8 FP16 | 100 tok/s 67 tok/s 39 tok/s | ~755 ms ~760 ms ~771 ms | |
#144 | GLM-4V | 9B | INT4 | 41 tok/s | ~1.6s | |
#150 | NVIDIA Nemotron 3 Nano 30B-A3B | 3.5B (30B active) | INT4 Q8 FP16 | 19 tok/s 11 tok/s 6 tok/s | ~5.2s ~5.2s ~5.7s | |
#158 | Granite 4.2 8B | 8B | INT4 Q8 | 62 tok/s 36 tok/s | ~1.5s ~1.6s | |
#159 | Gemma 4 E4B | 8B | INT4 Q8 | 62 tok/s 36 tok/s | ~1.5s ~1.6s | |
#166 | Phi-4 | 14B | INT4 | 39 tok/s | ~2.5s | |
#178 | OLMo 3 7B Think | 7B | INT4 Q8 | 49 tok/s 33 tok/s | ~1.3s ~1.4s | |
#179 | DeepSeek-R1 14B | 14B | INT4 | 40 tok/s | ~2.5s | |
#183 | Ministral 3 14B | 14B | INT4 | 26 tok/s | ~3.0s | |
#186 | Gemma 3 12B | 12B | INT4 | 45 tok/s | ~2.2s | |
#189 | Ministral 3 8B | 8B | INT4 Q8 | 45 tok/s 29 tok/s | ~1.5s ~1.7s | |
#191 | MiniCPM5-2B | 2B | INT4 Q8 FP16 | 144 tok/s 106 tok/s 67 tok/s | ~404 ms ~407 ms ~412 ms | |
#192 | Qwen3.5-2B | 2B | INT4 Q8 FP16 | 144 tok/s 106 tok/s 67 tok/s | ~404 ms ~407 ms ~412 ms | |
#194 | Qwen2.5-14B | 14B | INT4 | 39 tok/s | ~2.5s | |
#200 | Gemma 4 E2B | 5.1B | INT4 Q8 FP16 | 85 tok/s 56 tok/s 28 tok/s | ~949 ms ~956 ms ~1.1s | |
#202 | DeepSeek-R1 8B | 8B | INT4 Q8 | 63 tok/s 39 tok/s | ~1.5s ~1.5s | |
#204 | Qwen3-4B | 4B | INT4 Q8 FP16 | 100 tok/s 67 tok/s 39 tok/s | ~755 ms ~760 ms ~771 ms | |
#205 | Ministral 3 3B | 3B | INT4 Q8 FP16 | 81 tok/s 64 tok/s 42 tok/s | ~583 ms ~586 ms ~595 ms | |
#207 | Gemma 2 9B | 9B | INT4 Q8 | 56 tok/s 33 tok/s | ~1.6s ~1.8s | |
#208 | Qwen3.5-0.8B | 0.8B | INT4 Q8 FP16 | 204 tok/s 170 tok/s 124 tok/s | ~169 ms ~170 ms ~172 ms | |
#209 | Qwen3-14B | 14B | INT4 | 39 tok/s | ~2.5s | |
#210 | Gemma 3 4B | 4B | INT4 Q8 FP16 | 100 tok/s 67 tok/s 39 tok/s | ~755 ms ~760 ms ~771 ms | |
#211 | Qwen3-8B | 8B | INT4 Q8 | 62 tok/s 36 tok/s | ~1.5s ~1.6s | |
#213 | DeepSeek-R1 7B | 7B | INT4 Q8 | 70 tok/s 44 tok/s | ~1.3s ~1.3s | |
#214 | Qwen3-1.7B | 1.7B | INT4 Q8 FP16 | 155 tok/s 117 tok/s 76 tok/s | ~347 ms ~349 ms ~354 ms | |
#215 | Llama 3.1 8B | 8B | INT4 Q8 | 62 tok/s 36 tok/s | ~1.5s ~1.6s | |
#216 | Gemma 3 270M | 0.27B | INT4 Q8 FP16 | 232 tok/s 217 tok/s 187 tok/s | ~61 ms ~62 ms ~62 ms | |
#218 | Qwen3-0.6B | 0.6B | INT4 Q8 FP16 | 221 tok/s 190 tok/s 145 tok/s | ~127 ms ~128 ms ~129 ms | |
#219 | Llama 3 8B | 8B | INT4 Q8 | 62 tok/s 36 tok/s | ~1.5s ~1.6s | |
#221 | Phi-4-Mini | 3.8B | INT4 Q8 FP16 | 103 tok/s 69 tok/s 40 tok/s | ~720 ms ~725 ms ~735 ms | |
#223 | Qwen2.5-7B | 7B | INT4 Q8 | 68 tok/s 43 tok/s | ~1.3s ~1.3s | |
#224 | Ministral-8B-2410 | 8B | INT4 Q8 | 62 tok/s 36 tok/s | ~1.5s ~1.6s | |
#225 | DeepSeek-R1 1.5B | 1.5B | INT4 Q8 FP16 | 164 tok/s 126 tok/s 83 tok/s | ~308 ms ~310 ms ~314 ms | |
#226 | Llama 3.2 3B | 3B | INT4 Q8 FP16 | 118 tok/s 82 tok/s 49 tok/s | ~579 ms ~583 ms ~591 ms | |
#228 | Phi-3-mini | 3.8B | INT4 Q8 FP16 | 103 tok/s 69 tok/s 40 tok/s | ~720 ms ~725 ms ~735 ms | |
#229 | Gemma 3n E2B IT | 6B (2B active) | INT4 Q8 | 81 tok/s 70 tok/s | ~436 ms ~438 ms | |
#230 | Mistral-7B-Instruct-v0.1 | 7.3B | INT4 Q8 | 66 tok/s 41 tok/s | ~1.3s ~1.3s | |
#231 | Llama 3.2 1B | 1B | INT4 Q8 FP16 | 189 tok/s 154 tok/s 108 tok/s | ~213 ms ~214 ms ~217 ms | |
#232 | Gemma 2 2B | 2B | INT4 Q8 FP16 | 144 tok/s 106 tok/s 67 tok/s | ~404 ms ~407 ms ~412 ms | |
#233 | Phi-3-medium | 14B | INT4 | 39 tok/s | ~2.5s | |
#234 | OLMo 3 7B Instruct | 7B | INT4 Q8 | 49 tok/s 33 tok/s | ~1.3s ~1.4s | |
#236 | Qwen2-7B | 7B | INT4 Q8 | 68 tok/s 43 tok/s | ~1.3s ~1.3s | |
#237 | Phi-3-small | 7B | INT4 Q8 | 68 tok/s 43 tok/s | ~1.3s ~1.3s | |
#238 | Gemma 3 1B | 1B | INT4 Q8 FP16 | 189 tok/s 154 tok/s 108 tok/s | ~213 ms ~214 ms ~217 ms | |
#239 | Mistral-7B-Instruct-v0.2 | 7.3B | INT4 Q8 | 66 tok/s 41 tok/s | ~1.3s ~1.3s | |
#241 | Gemma 1 7B | 7B | INT4 Q8 | 49 tok/s 33 tok/s | ~1.3s ~1.4s | |
#242 | Gemma 1 2B | 2B | INT4 Q8 FP16 | 152 tok/s 110 tok/s 69 tok/s | ~404 ms ~407 ms ~412 ms | |
#243 | ChatGLM3-6B | 6B | INT4 Q8 | 55 tok/s 40 tok/s | ~1.1s ~1.1s | |
#244 | ChatGLM2-6B | 6B | INT4 Q8 | 55 tok/s 40 tok/s | ~1.1s ~1.1s | |
#245 | ChatGLM-6B | 6B | INT4 Q8 | 55 tok/s 40 tok/s | ~1.1s ~1.1s | |
Unranked Models (Sorted by Speed) | ||||||
- | DINOv3 ViT-L/16 | 0.3B | INT4 Q8 FP16 | 250 tok/s 229 tok/s 193 tok/s | ~67 ms ~67 ms ~68 ms | |
- | Qwen2-0.5B | 0.5B | INT4 Q8 FP16 | 230 tok/s 202 tok/s 158 tok/s | ~106 ms ~107 ms ~108 ms | |
- | Qwen2.5-0.5B | 0.5B | INT4 Q8 FP16 | 230 tok/s 202 tok/s 158 tok/s | ~106 ms ~107 ms ~108 ms | |
- | ERNIE-4.5-0.3B | 0.3B | INT4 Q8 FP16 | 226 tok/s 210 tok/s 180 tok/s | ~67 ms ~68 ms ~69 ms | |
- | ERNIE-4.5-0.3B-Base | 0.3B | INT4 Q8 FP16 | 226 tok/s 210 tok/s 180 tok/s | ~67 ms ~68 ms ~69 ms | |
- | Liquid D1-Omni 600M | 0.6B | INT4 Q8 FP16 | 221 tok/s 190 tok/s 145 tok/s | ~127 ms ~128 ms ~129 ms | |
- | PixArt-α XL 2 1024-MS | 0.61B | INT4 Q8 FP16 | 220 tok/s 189 tok/s 144 tok/s | ~129 ms ~129 ms ~131 ms | |
- | PixArt-Σ XL 2 1024-MS | 0.61B | INT4 Q8 FP16 | 220 tok/s 189 tok/s 144 tok/s | ~129 ms ~129 ms ~131 ms | |
- | Nemotron 3.5 Parse | 0.63B | INT4 Q8 FP16 | 218 tok/s 187 tok/s 141 tok/s | ~133 ms ~134 ms ~136 ms | |
- | SD 2.1 Turbo | 0.86B | INT4 Q8 FP16 | 200 tok/s 165 tok/s 119 tok/s | ~182 ms ~183 ms ~185 ms | |
- | Stable Diffusion 1.4 | 0.86B | INT4 Q8 FP16 | 200 tok/s 165 tok/s 119 tok/s | ~182 ms ~183 ms ~185 ms | |
- | Stable Diffusion 2.1 | 0.86B | INT4 Q8 FP16 | 200 tok/s 165 tok/s 119 tok/s | ~182 ms ~183 ms ~185 ms | |
- | Falcon-1B | 1B | INT4 Q8 FP16 | 198 tok/s 159 tok/s 111 tok/s | ~212 ms ~214 ms ~216 ms | |
- | Falcon3-1B | 1B | INT4 Q8 FP16 | 189 tok/s 154 tok/s 108 tok/s | ~213 ms ~214 ms ~217 ms | |
- | MiniCPM-V 4.7 1B | 1B | INT4 Q8 FP16 | 189 tok/s 154 tok/s 108 tok/s | ~213 ms ~214 ms ~217 ms | |
- | Kandinsky 2.2 Decoder | 1.22B | INT4 Q8 FP16 | 177 tok/s 140 tok/s 96 tok/s | ~255 ms ~256 ms ~260 ms | |
- | Wan 2.1 T2V 1.3B | 1.3B | INT4 Q8 FP16 | 173 tok/s 136 tok/s 92 tok/s | ~269 ms ~271 ms ~274 ms | |
- | Qwen2-1.5B | 1.5B | INT4 Q8 FP16 | 164 tok/s 126 tok/s 83 tok/s | ~308 ms ~310 ms ~314 ms | |
- | Qwen2.5-1.5B | 1.5B | INT4 Q8 FP16 | 164 tok/s 126 tok/s 83 tok/s | ~308 ms ~310 ms ~314 ms | |
- | SVD Image-to-Video XT | 1.5B | INT4 Q8 FP16 | 164 tok/s 126 tok/s 83 tok/s | ~308 ms ~310 ms ~314 ms | |
- | SVD Image-to-Video XT 1.1 | 1.5B | INT4 Q8 FP16 | 164 tok/s 126 tok/s 83 tok/s | ~308 ms ~310 ms ~314 ms | |
- | LFM3 1.7B | 1.7B | INT4 Q8 FP16 | 155 tok/s 117 tok/s 76 tok/s | ~347 ms ~349 ms ~354 ms | |
- | LFM3 1.7B Base | 1.7B | INT4 Q8 FP16 | 155 tok/s 117 tok/s 76 tok/s | ~347 ms ~349 ms ~354 ms | |
- | Spark X2.5 1.7B | 1.7B | INT4 Q8 FP16 | 155 tok/s 117 tok/s 76 tok/s | ~347 ms ~349 ms ~354 ms | |
- | Hy-MT2 1.8B | 1.8B | INT4 Q8 FP16 | 151 tok/s 113 tok/s 73 tok/s | ~365 ms ~367 ms ~372 ms | |
- | CogVideoX 2B | 2B | INT4 Q8 FP16 | 144 tok/s 106 tok/s 67 tok/s | ~404 ms ~407 ms ~412 ms | |
- | LFM3 Audio 2B | 2B | INT4 Q8 FP16 | 144 tok/s 106 tok/s 67 tok/s | ~404 ms ~407 ms ~412 ms | |
- | LFM3 Omni 2B | 2B | INT4 Q8 FP16 | 144 tok/s 106 tok/s 67 tok/s | ~404 ms ~407 ms ~412 ms | |
- | LFM3 VL 2B | 2B | INT4 Q8 FP16 | 144 tok/s 106 tok/s 67 tok/s | ~404 ms ~407 ms ~412 ms | |
- | Liquid D1 2B | 2B | INT4 Q8 FP16 | 144 tok/s 106 tok/s 67 tok/s | ~404 ms ~407 ms ~412 ms | |
- | LTX-Video 0.9.1 | 2B | INT4 Q8 FP16 | 144 tok/s 106 tok/s 67 tok/s | ~404 ms ~407 ms ~412 ms | |
- | Moondream 3.1 | 9B (2B active) | INT4 Q8 | 144 tok/s 101 tok/s | ~455 ms ~496 ms | |
- | Stable Diffusion 3 Medium | 2B | INT4 Q8 FP16 | 144 tok/s 106 tok/s 67 tok/s | ~404 ms ~407 ms ~412 ms | |
- | Kandinsky 3.0 | 2.1B | INT4 Q8 FP16 | 141 tok/s 103 tok/s 65 tok/s | ~422 ms ~425 ms ~430 ms | |
- | LTX-2 | 2.2B | INT4 Q8 FP16 | 138 tok/s 100 tok/s 63 tok/s | ~439 ms ~442 ms ~448 ms | |
- | SDXL 1.0 Refiner | 2.31B | INT4 Q8 FP16 | 135 tok/s 97 tok/s 60 tok/s | ~459 ms ~461 ms ~468 ms | |
- | Stable Diffusion 3.5 Medium | 2.5B | INT4 Q8 FP16 | 130 tok/s 93 tok/s 57 tok/s | ~492 ms ~495 ms ~502 ms | |
- | SDXL 1.0 Base | 2.56B | INT4 Q8 FP16 | 128 tok/s 91 tok/s 56 tok/s | ~502 ms ~506 ms ~512 ms | |
- | SDXL Turbo | 2.56B | INT4 Q8 FP16 | 128 tok/s 91 tok/s 56 tok/s | ~502 ms ~506 ms ~512 ms | |
- | Falcon-3B | 3B | INT4 Q8 FP16 | 124 tok/s 85 tok/s 50 tok/s | ~579 ms ~583 ms ~591 ms | |
- | CroissantLLM Base | 1.3B | INT4 Q8 FP16 | 122 tok/s 104 tok/s 76 tok/s | ~271 ms ~273 ms ~276 ms | |
- | Phi-1 | 1.3B | INT4 Q8 FP16 | 122 tok/s 104 tok/s 76 tok/s | ~271 ms ~273 ms ~276 ms | |
- | Phi-1.5 | 1.3B | INT4 Q8 FP16 | 122 tok/s 104 tok/s 76 tok/s | ~271 ms ~273 ms ~276 ms | |
- | DeepSeek-R1 3B | 3B | INT4 Q8 FP16 | 119 tok/s 83 tok/s 49 tok/s | ~579 ms ~583 ms ~591 ms | |
- | Mellum 2.1 12B A2.5B Thinking | 12B (2.5B active) | INT4 | 119 tok/s | ~566 ms | |
- | Falcon3-3B | 3B | INT4 Q8 FP16 | 118 tok/s 82 tok/s 49 tok/s | ~579 ms ~583 ms ~591 ms | |
- | LFM2-VL 3B | 3B | INT4 Q8 FP16 | 118 tok/s 82 tok/s 49 tok/s | ~579 ms ~583 ms ~591 ms | |
- | Liquid D1 3B | 3B | INT4 Q8 FP16 | 118 tok/s 82 tok/s 49 tok/s | ~579 ms ~583 ms ~591 ms | |
- | Liquid D1-VL 3B | 3B | INT4 Q8 FP16 | 118 tok/s 82 tok/s 49 tok/s | ~579 ms ~583 ms ~591 ms | |
- | Liquid LFM2-VL 3B D1 | 3B | INT4 Q8 FP16 | 118 tok/s 82 tok/s 49 tok/s | ~579 ms ~583 ms ~591 ms | |
- | Qwen2.5-3B | 3B | INT4 Q8 FP16 | 118 tok/s 82 tok/s 49 tok/s | ~579 ms ~583 ms ~591 ms | |
- | FLUX.2 Klein 4B | 4B | INT4 Q8 FP16 | 100 tok/s 67 tok/s 39 tok/s | ~755 ms ~760 ms ~771 ms | |
- | FrogNano 4B | 4B | INT4 Q8 FP16 | 100 tok/s 67 tok/s 39 tok/s | ~755 ms ~760 ms ~771 ms | |
- | Mage-VL Cowork | 4B | INT4 Q8 FP16 | 100 tok/s 67 tok/s 39 tok/s | ~755 ms ~760 ms ~771 ms | |
- | Spark X2.5 4B | 4B | INT4 Q8 FP16 | 100 tok/s 67 tok/s 39 tok/s | ~755 ms ~760 ms ~771 ms | |
- | EmbeddingGemma 2 | 2B | INT4 Q8 FP16 | 96 tok/s 79 tok/s 55 tok/s | ~408 ms ~410 ms ~415 ms | |
- | CogVideoX 1.5 5B | 5B | INT4 Q8 FP16 | 86 tok/s 56 tok/s 30 tok/s | ~932 ms ~938 ms ~1.0s | |
- | CogVideoX 5B | 5B | INT4 Q8 FP16 | 86 tok/s 56 tok/s 30 tok/s | ~932 ms ~938 ms ~1.0s | |
- | Wan 2.2 TI2V 5B | 5B | INT4 Q8 FP16 | 86 tok/s 56 tok/s 30 tok/s | ~932 ms ~938 ms ~1.0s | |
- | Phi-2 | 2.7B | INT4 Q8 FP16 | 85 tok/s 68 tok/s 45 tok/s | ~530 ms ~534 ms ~541 ms | |
- | MaLLaM-3B | 3B | INT4 Q8 FP16 | 81 tok/s 64 tok/s 42 tok/s | ~583 ms ~586 ms ~595 ms | |
- | SmolLM3 3B | 3B | INT4 Q8 FP16 | 81 tok/s 64 tok/s 42 tok/s | ~583 ms ~586 ms ~595 ms | |
- | Falcon-7B | 7B | INT4 Q8 | 71 tok/s 44 tok/s | ~1.3s ~1.3s | |
- | AuraFlow v0.2 | 6.8B | INT4 Q8 | 70 tok/s 44 tok/s | ~1.2s ~1.3s | |
- | AuraFlow v0.3 | 6.8B | INT4 Q8 | 70 tok/s 44 tok/s | ~1.2s ~1.3s | |
- | Falcon3-7B | 7B | INT4 Q8 | 68 tok/s 43 tok/s | ~1.3s ~1.3s | |
- | Hy-MT2 7B | 7B | INT4 Q8 | 68 tok/s 43 tok/s | ~1.3s ~1.3s | |
- | Mistral-7B-v0.1 | 7.3B | INT4 Q8 | 66 tok/s 41 tok/s | ~1.3s ~1.3s | |
- | Youtu Parsing Omni | 8B | INT4 Q8 | 63 tok/s 39 tok/s | ~1.5s ~1.5s | |
- | Stable Diffusion 3.5 Large | 8.1B | INT4 Q8 | 61 tok/s 36 tok/s | ~1.5s ~1.6s | |
- | Stable Diffusion 3.5 Large Turbo | 8.1B | INT4 Q8 | 61 tok/s 36 tok/s | ~1.5s ~1.6s | |
- | FLUX.2 Klein 9B | 9B | INT4 Q8 | 56 tok/s 33 tok/s | ~1.6s ~1.8s | |
- | LensVLM 9B | 9B | INT4 Q8 | 56 tok/s 33 tok/s | ~1.6s ~1.8s | |
- | MiMo V2.6 Distill Qwen 9B | 9B | INT4 Q8 | 56 tok/s 33 tok/s | ~1.6s ~1.8s | |
- | ChatGLM3-6B-32K | 6B | INT4 Q8 | 55 tok/s 40 tok/s | ~1.1s ~1.1s | |
- | Yi-6B | 6B | INT4 Q8 | 55 tok/s 40 tok/s | ~1.1s ~1.1s | |
- | Falcon3-10B | 10B | INT4 Q8 | 52 tok/s 28 tok/s | ~1.8s ~2.1s | |
- | Mochi 1 Preview | 10B | INT4 Q8 | 52 tok/s 28 tok/s | ~1.8s ~2.1s | |
- | Falcon2-11B | 11B | INT4 Q8 | 50 tok/s 27 tok/s | ~2.0s ~2.4s | |
- | Hunyuan Lite | 7B | INT4 Q8 | 49 tok/s 33 tok/s | ~1.3s ~1.4s | |
- | OLMo 3 7B Base | 7B | INT4 Q8 | 49 tok/s 33 tok/s | ~1.3s ~1.4s | |
- | SEA-LION-7B | 7.1B | INT4 Q8 | 49 tok/s 33 tok/s | ~1.3s ~1.4s | |
- | SEA-LION-7B-Instruct | 7.1B | INT4 Q8 | 49 tok/s 33 tok/s | ~1.3s ~1.4s | |
- | FLUX.1 Canny Dev | 11.9B | INT4 | 45 tok/s | ~2.2s | |
- | FLUX.1 Depth Dev | 11.9B | INT4 | 45 tok/s | ~2.2s | |
- | FLUX.1 Dev | 11.9B | INT4 | 45 tok/s | ~2.2s | |
- | FLUX.1 Fill Dev | 11.9B | INT4 | 45 tok/s | ~2.2s | |
- | FLUX.1 Schnell | 11.9B | INT4 | 45 tok/s | ~2.2s | |
- | Sahabat-AI-Llama3-8B-Instruct | 8B | INT4 Q8 | 45 tok/s 29 tok/s | ~1.5s ~1.7s | |
- | Typhoon-2-8B | 8B | INT4 Q8 | 45 tok/s 29 tok/s | ~1.5s ~1.7s | |
- | HunyuanVideo 1.5 720P T2V | 13B | INT4 | 42 tok/s | ~2.4s | |
- | GLM-4-9B | 9B | INT4 | 41 tok/s | ~1.6s | |
- | GLM-4-9B-Chat | 9B | INT4 | 41 tok/s | ~1.6s | |
- | GLM-4-9B-Chat-1M | 9B | INT4 | 41 tok/s | ~1.6s | |
- | Yi-9B | 9B | INT4 | 41 tok/s | ~1.6s | |
- | Sahabat-AI-Gemma2-9B | 9.2B | INT4 | 40 tok/s | ~1.7s | |
- | Sahabat-AI-Gemma2-9B-Instruct | 9.2B | INT4 | 40 tok/s | ~1.7s | |
- | Wan 2.1 I2V 14B 720P | 14B | INT4 | 39 tok/s | ~2.5s | |
- | Wan 2.1 T2V 14B | 14B | INT4 | 39 tok/s | ~2.5s | |
- | Wan 2.2 T2V A14B | 14B | INT4 | 39 tok/s | ~2.5s | |
- | FLUX.2 Dev | 15B | INT4 | 37 tok/s | ~2.7s | |
- | GreenMind-14B-R1 | 14B | INT4 | 26 tok/s | ~3.0s | |
Inference Capacity
Maximum model parameter class runnable by weight precision.
Context:
4-bit
14B Models
8-bit
8B Models
16-bit
3B Models
Fine-Tuning Capacity
Hardware capacity for local training and adapter fine-tuning.
Context Length:
QLoRA
14B Models
LoRA
8B Models
Full Parameter Training
1B Models
Workload Recommendations
Guidance for optimal precision and operational ceilings on AMD RX 7700 XT (12GB).
Inference Sweet Spot
Optimal for 8B models across extended context (32k+). 14B models fit comfortably at Q4 precision with standard context.
Bandwidth & Speed Profile
With 432 GB/s aggregate bandwidth, batch size 1 inference operates in a memory-bandwidth bound regime. Generates approximately 96 tok/s on an 8B Q4 model and 11 tok/s on a 70B Q4 model.
Frequently Asked Questions
©2025 ApX Machine Learning