AMD RX 6900 XT (16GB)
The AMD RX 6900 XT (16GB) provides 16 GB of memory with 512 GB/s bandwidth, supporting local inference via ROCm and Vulkan acceleration.
Memory
16 GB
Usable Memory Ceiling
16 GB
Bandwidth
512 GB/s
Max Inference Class
14B Models (Q4)
TDP
300W
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 6900 XT (16GB)
Inference throughput, memory compatibility, and generation speeds for open-weights LLMs on AMD RX 6900 XT (16GB).
Sort by:
Context:
KV Cache:
GPUs:
| Rank | Model | Parameters | Precision | TPS (Approx.) | TTFT | Can Run |
|---|---|---|---|---|---|---|
#48 | Qwen 3.8 27B | 27B | INT4 | 23 tok/s | ~8.5s | |
#93 | Qwen3.5-27B | 27B | INT4 | 23 tok/s | ~8.5s | |
#111 | MiMo V2 Flash | 15B (309B active) | INT4 | 2 tok/s | ~86.3s | |
#112 | Phi-4 Reasoning Plus | 14B | INT4 | 34 tok/s | ~3.8s | |
#117 | Gemma 4 26B A4B | 25.2B (3.8B active) | INT4 | 97 tok/s | ~1.4s | |
#125 | Qwen3.5-9B | 9B | INT4 Q8 | 64 tok/s 40 tok/s | ~2.5s ~2.5s | |
#128 | K2 Horizon 7B | 7B | INT4 Q8 FP16 | 77 tok/s 50 tok/s 25 tok/s | ~1.9s ~1.9s ~2.3s | |
#135 | Gemma 4 12B | 11.95B | INT4 Q8 | 38 tok/s 24 tok/s | ~3.3s ~3.9s | |
#140 | Qwen3.5-4B | 4B | INT4 Q8 FP16 | 111 tok/s 76 tok/s 45 tok/s | ~1.1s ~1.1s ~1.2s | |
#143 | GPT-OSS 20B | 21B (3.6B active) | INT4 | 47 tok/s | ~1.4s | |
#144 | GLM-4V | 9B | INT4 Q8 | 47 tok/s 32 tok/s | ~2.5s ~2.7s | |
#150 | NVIDIA Nemotron 3 Nano 30B-A3B | 3.5B (30B active) | INT4 Q8 FP16 | 22 tok/s 13 tok/s 7 tok/s | ~7.8s ~7.8s ~7.9s | |
#158 | Granite 4.2 8B | 8B | INT4 Q8 | 70 tok/s 44 tok/s | ~2.2s ~2.2s | |
#159 | Gemma 4 E4B | 8B | INT4 Q8 | 70 tok/s 44 tok/s | ~2.2s ~2.2s | |
#166 | Phi-4 | 14B | INT4 Q8 | 45 tok/s 25 tok/s | ~3.8s ~4.5s | |
#167 | Gemma 3 27B | 27B | INT4 | 23 tok/s | ~8.5s | |
#178 | OLMo 3 7B Think | 7B | INT4 Q8 | 57 tok/s 41 tok/s | ~1.9s ~2.0s | |
#179 | DeepSeek-R1 14B | 14B | INT4 Q8 | 47 tok/s 25 tok/s | ~3.8s ~4.5s | |
#183 | Ministral 3 14B | 14B | INT4 | 34 tok/s | ~3.8s | |
#186 | Gemma 3 12B | 12B | INT4 Q8 | 51 tok/s 30 tok/s | ~3.3s ~3.6s | |
#188 | Mistral-Small-2501 | 24B | INT4 | 27 tok/s | ~7.0s | |
#189 | Ministral 3 8B | 8B | INT4 Q8 | 52 tok/s 37 tok/s | ~2.2s ~2.2s | |
#191 | MiniCPM5-2B | 2B | INT4 Q8 FP16 | 156 tok/s 118 tok/s 76 tok/s | ~608 ms ~610 ms ~614 ms | |
#192 | Qwen3.5-2B | 2B | INT4 Q8 FP16 | 156 tok/s 118 tok/s 76 tok/s | ~608 ms ~610 ms ~614 ms | |
#193 | Gemma 2 27B | 27B | INT4 | 23 tok/s | ~8.5s | |
#194 | Qwen2.5-14B | 14B | INT4 Q8 | 45 tok/s 25 tok/s | ~3.8s ~4.5s | |
#200 | Gemma 4 E2B | 5.1B | INT4 Q8 FP16 | 96 tok/s 64 tok/s 36 tok/s | ~1.4s ~1.4s ~1.4s | |
#202 | DeepSeek-R1 8B | 8B | INT4 Q8 | 72 tok/s 45 tok/s | ~2.2s ~2.2s | |
#204 | Qwen3-4B | 4B | INT4 Q8 FP16 | 111 tok/s 76 tok/s 45 tok/s | ~1.1s ~1.1s ~1.2s | |
#205 | Ministral 3 3B | 3B | INT4 Q8 FP16 | 91 tok/s 73 tok/s 48 tok/s | ~876 ms ~878 ms ~885 ms | |
#207 | Gemma 2 9B | 9B | INT4 Q8 | 64 tok/s 40 tok/s | ~2.5s ~2.5s | |
#208 | Qwen3.5-0.8B | 0.8B | INT4 Q8 FP16 | 214 tok/s 182 tok/s 136 tok/s | ~251 ms ~252 ms ~254 ms | |
#209 | Qwen3-14B | 14B | INT4 Q8 | 45 tok/s 25 tok/s | ~3.8s ~4.5s | |
#210 | Gemma 3 4B | 4B | INT4 Q8 FP16 | 111 tok/s 76 tok/s 45 tok/s | ~1.1s ~1.1s ~1.2s | |
#211 | Qwen3-8B | 8B | INT4 Q8 | 70 tok/s 44 tok/s | ~2.2s ~2.2s | |
#213 | DeepSeek-R1 7B | 7B | INT4 Q8 FP16 | 79 tok/s 50 tok/s 26 tok/s | ~1.9s ~1.9s ~2.1s | |
#214 | Qwen3-1.7B | 1.7B | INT4 Q8 FP16 | 167 tok/s 129 tok/s 86 tok/s | ~521 ms ~522 ms ~526 ms | |
#215 | Llama 3.1 8B | 8B | INT4 Q8 | 70 tok/s 44 tok/s | ~2.2s ~2.2s | |
#216 | Gemma 3 270M | 0.27B | INT4 Q8 FP16 | 239 tok/s 226 tok/s 198 tok/s | ~88 ms ~88 ms ~89 ms | |
#218 | Qwen3-0.6B | 0.6B | INT4 Q8 FP16 | 229 tok/s 201 tok/s 157 tok/s | ~187 ms ~188 ms ~189 ms | |
#219 | Llama 3 8B | 8B | INT4 Q8 | 70 tok/s 44 tok/s | ~2.2s ~2.2s | |
#221 | Phi-4-Mini | 3.8B | INT4 Q8 FP16 | 114 tok/s 79 tok/s 47 tok/s | ~1.1s ~1.1s ~1.1s | |
#223 | Qwen2.5-7B | 7B | INT4 Q8 FP16 | 77 tok/s 50 tok/s 25 tok/s | ~1.9s ~1.9s ~2.3s | |
#224 | Ministral-8B-2410 | 8B | INT4 Q8 | 70 tok/s 44 tok/s | ~2.2s ~2.2s | |
#225 | DeepSeek-R1 1.5B | 1.5B | INT4 Q8 FP16 | 175 tok/s 138 tok/s 93 tok/s | ~461 ms ~463 ms ~466 ms | |
#226 | Llama 3.2 3B | 3B | INT4 Q8 FP16 | 130 tok/s 92 tok/s 56 tok/s | ~872 ms ~875 ms ~882 ms | |
#228 | Phi-3-mini | 3.8B | INT4 Q8 FP16 | 114 tok/s 79 tok/s 47 tok/s | ~1.1s ~1.1s ~1.1s | |
#229 | Gemma 3n E2B IT | 6B (2B active) | INT4 Q8 FP16 | 91 tok/s 79 tok/s 55 tok/s | ~653 ms ~654 ms ~715 ms | |
#230 | Mistral-7B-Instruct-v0.1 | 7.3B | INT4 Q8 FP16 | 75 tok/s 48 tok/s 24 tok/s | ~2.0s ~2.0s ~2.4s | |
#231 | Llama 3.2 1B | 1B | INT4 Q8 FP16 | 200 tok/s 166 tok/s 120 tok/s | ~317 ms ~318 ms ~320 ms | |
#232 | Gemma 2 2B | 2B | INT4 Q8 FP16 | 156 tok/s 118 tok/s 76 tok/s | ~608 ms ~610 ms ~614 ms | |
#233 | Phi-3-medium | 14B | INT4 Q8 | 45 tok/s 25 tok/s | ~3.8s ~4.5s | |
#234 | OLMo 3 7B Instruct | 7B | INT4 Q8 | 57 tok/s 41 tok/s | ~1.9s ~2.0s | |
#236 | Qwen2-7B | 7B | INT4 Q8 FP16 | 77 tok/s 50 tok/s 25 tok/s | ~1.9s ~1.9s ~2.3s | |
#237 | Phi-3-small | 7B | INT4 Q8 FP16 | 77 tok/s 50 tok/s 25 tok/s | ~1.9s ~1.9s ~2.3s | |
#238 | Gemma 3 1B | 1B | INT4 Q8 FP16 | 200 tok/s 166 tok/s 120 tok/s | ~317 ms ~318 ms ~320 ms | |
#239 | Mistral-7B-Instruct-v0.2 | 7.3B | INT4 Q8 FP16 | 75 tok/s 48 tok/s 24 tok/s | ~2.0s ~2.0s ~2.4s | |
#241 | Gemma 1 7B | 7B | INT4 Q8 | 57 tok/s 41 tok/s | ~1.9s ~2.0s | |
#242 | Gemma 1 2B | 2B | INT4 Q8 FP16 | 164 tok/s 122 tok/s 78 tok/s | ~607 ms ~609 ms ~614 ms | |
#243 | ChatGLM3-6B | 6B | INT4 Q8 FP16 | 63 tok/s 46 tok/s 27 tok/s | ~1.7s ~1.7s ~1.8s | |
#244 | ChatGLM2-6B | 6B | INT4 Q8 FP16 | 63 tok/s 46 tok/s 27 tok/s | ~1.7s ~1.7s ~1.8s | |
#245 | ChatGLM-6B | 6B | INT4 Q8 FP16 | 63 tok/s 46 tok/s 27 tok/s | ~1.7s ~1.7s ~1.8s | |
Unranked Models (Sorted by Speed) | ||||||
- | DINOv3 ViT-L/16 | 0.3B | INT4 Q8 FP16 | 255 tok/s 236 tok/s 203 tok/s | ~97 ms ~97 ms ~98 ms | |
- | Qwen2-0.5B | 0.5B | INT4 Q8 FP16 | 237 tok/s 211 tok/s 170 tok/s | ~156 ms ~157 ms ~158 ms | |
- | Qwen2.5-0.5B | 0.5B | INT4 Q8 FP16 | 237 tok/s 211 tok/s 170 tok/s | ~156 ms ~157 ms ~158 ms | |
- | ERNIE-4.5-0.3B | 0.3B | INT4 Q8 FP16 | 234 tok/s 220 tok/s 191 tok/s | ~97 ms ~97 ms ~98 ms | |
- | ERNIE-4.5-0.3B-Base | 0.3B | INT4 Q8 FP16 | 234 tok/s 220 tok/s 191 tok/s | ~97 ms ~97 ms ~98 ms | |
- | Liquid D1-Omni 600M | 0.6B | INT4 Q8 FP16 | 229 tok/s 201 tok/s 157 tok/s | ~187 ms ~188 ms ~189 ms | |
- | PixArt-α XL 2 1024-MS | 0.61B | INT4 Q8 FP16 | 228 tok/s 200 tok/s 156 tok/s | ~190 ms ~191 ms ~192 ms | |
- | PixArt-Σ XL 2 1024-MS | 0.61B | INT4 Q8 FP16 | 228 tok/s 200 tok/s 156 tok/s | ~190 ms ~191 ms ~192 ms | |
- | Nemotron 3.5 Parse | 0.63B | INT4 Q8 FP16 | 226 tok/s 197 tok/s 154 tok/s | ~197 ms ~198 ms ~199 ms | |
- | SD 2.1 Turbo | 0.86B | INT4 Q8 FP16 | 210 tok/s 177 tok/s 131 tok/s | ~270 ms ~271 ms ~273 ms | |
- | Stable Diffusion 1.4 | 0.86B | INT4 Q8 FP16 | 210 tok/s 177 tok/s 131 tok/s | ~270 ms ~271 ms ~273 ms | |
- | Stable Diffusion 2.1 | 0.86B | INT4 Q8 FP16 | 210 tok/s 177 tok/s 131 tok/s | ~270 ms ~271 ms ~273 ms | |
- | Falcon-1B | 1B | INT4 Q8 FP16 | 208 tok/s 171 tok/s 123 tok/s | ~317 ms ~318 ms ~320 ms | |
- | Falcon3-1B | 1B | INT4 Q8 FP16 | 200 tok/s 166 tok/s 120 tok/s | ~317 ms ~318 ms ~320 ms | |
- | MiniCPM-V 4.7 1B | 1B | INT4 Q8 FP16 | 200 tok/s 166 tok/s 120 tok/s | ~317 ms ~318 ms ~320 ms | |
- | Kandinsky 2.2 Decoder | 1.22B | INT4 Q8 FP16 | 188 tok/s 152 tok/s 107 tok/s | ~381 ms ~382 ms ~385 ms | |
- | Wan 2.1 T2V 1.3B | 1.3B | INT4 Q8 FP16 | 185 tok/s 148 tok/s 103 tok/s | ~402 ms ~404 ms ~407 ms | |
- | Qwen2-1.5B | 1.5B | INT4 Q8 FP16 | 175 tok/s 138 tok/s 93 tok/s | ~461 ms ~463 ms ~466 ms | |
- | Qwen2.5-1.5B | 1.5B | INT4 Q8 FP16 | 175 tok/s 138 tok/s 93 tok/s | ~461 ms ~463 ms ~466 ms | |
- | SVD Image-to-Video XT | 1.5B | INT4 Q8 FP16 | 175 tok/s 138 tok/s 93 tok/s | ~461 ms ~463 ms ~466 ms | |
- | SVD Image-to-Video XT 1.1 | 1.5B | INT4 Q8 FP16 | 175 tok/s 138 tok/s 93 tok/s | ~461 ms ~463 ms ~466 ms | |
- | LFM3 1.7B | 1.7B | INT4 Q8 FP16 | 167 tok/s 129 tok/s 86 tok/s | ~521 ms ~522 ms ~526 ms | |
- | LFM3 1.7B Base | 1.7B | INT4 Q8 FP16 | 167 tok/s 129 tok/s 86 tok/s | ~521 ms ~522 ms ~526 ms | |
- | Spark X2.5 1.7B | 1.7B | INT4 Q8 FP16 | 167 tok/s 129 tok/s 86 tok/s | ~521 ms ~522 ms ~526 ms | |
- | Hy-MT2 1.8B | 1.8B | INT4 Q8 FP16 | 163 tok/s 125 tok/s 83 tok/s | ~548 ms ~550 ms ~554 ms | |
- | CogVideoX 2B | 2B | INT4 Q8 FP16 | 156 tok/s 118 tok/s 76 tok/s | ~608 ms ~610 ms ~614 ms | |
- | LFM3 Audio 2B | 2B | INT4 Q8 FP16 | 156 tok/s 118 tok/s 76 tok/s | ~608 ms ~610 ms ~614 ms | |
- | LFM3 Omni 2B | 2B | INT4 Q8 FP16 | 156 tok/s 118 tok/s 76 tok/s | ~608 ms ~610 ms ~614 ms | |
- | LFM3 VL 2B | 2B | INT4 Q8 FP16 | 156 tok/s 118 tok/s 76 tok/s | ~608 ms ~610 ms ~614 ms | |
- | Liquid D1 2B | 2B | INT4 Q8 FP16 | 156 tok/s 118 tok/s 76 tok/s | ~608 ms ~610 ms ~614 ms | |
- | LTX-Video 0.9.1 | 2B | INT4 Q8 FP16 | 156 tok/s 118 tok/s 76 tok/s | ~608 ms ~610 ms ~614 ms | |
- | Moondream 3.1 | 9B (2B active) | INT4 Q8 | 156 tok/s 118 tok/s | ~684 ms ~686 ms | |
- | Stable Diffusion 3 Medium | 2B | INT4 Q8 FP16 | 156 tok/s 118 tok/s 76 tok/s | ~608 ms ~610 ms ~614 ms | |
- | Kandinsky 3.0 | 2.1B | INT4 Q8 FP16 | 153 tok/s 115 tok/s 74 tok/s | ~634 ms ~636 ms ~641 ms | |
- | LTX-2 | 2.2B | INT4 Q8 FP16 | 150 tok/s 112 tok/s 71 tok/s | ~661 ms ~663 ms ~668 ms | |
- | SDXL 1.0 Refiner | 2.31B | INT4 Q8 FP16 | 147 tok/s 109 tok/s 69 tok/s | ~690 ms ~692 ms ~697 ms | |
- | Stable Diffusion 3.5 Medium | 2.5B | INT4 Q8 FP16 | 142 tok/s 104 tok/s 65 tok/s | ~740 ms ~743 ms ~748 ms | |
- | SDXL 1.0 Base | 2.56B | INT4 Q8 FP16 | 140 tok/s 102 tok/s 64 tok/s | ~756 ms ~759 ms ~764 ms | |
- | SDXL Turbo | 2.56B | INT4 Q8 FP16 | 140 tok/s 102 tok/s 64 tok/s | ~756 ms ~759 ms ~764 ms | |
- | Falcon-3B | 3B | INT4 Q8 FP16 | 136 tok/s 95 tok/s 58 tok/s | ~872 ms ~875 ms ~882 ms | |
- | CroissantLLM Base | 1.3B | INT4 Q8 FP16 | 134 tok/s 116 tok/s 86 tok/s | ~405 ms ~406 ms ~409 ms | |
- | Phi-1 | 1.3B | INT4 Q8 FP16 | 134 tok/s 116 tok/s 86 tok/s | ~405 ms ~406 ms ~409 ms | |
- | Phi-1.5 | 1.3B | INT4 Q8 FP16 | 134 tok/s 116 tok/s 86 tok/s | ~405 ms ~406 ms ~409 ms | |
- | DeepSeek-R1 3B | 3B | INT4 Q8 FP16 | 131 tok/s 93 tok/s 57 tok/s | ~872 ms ~875 ms ~882 ms | |
- | Mellum 2.1 12B A2.5B Thinking | 12B (2.5B active) | INT4 Q8 | 131 tok/s 94 tok/s | ~852 ms ~928 ms | |
- | Falcon3-3B | 3B | INT4 Q8 FP16 | 130 tok/s 92 tok/s 56 tok/s | ~872 ms ~875 ms ~882 ms | |
- | LFM2-VL 3B | 3B | INT4 Q8 FP16 | 130 tok/s 92 tok/s 56 tok/s | ~872 ms ~875 ms ~882 ms | |
- | Liquid D1 3B | 3B | INT4 Q8 FP16 | 130 tok/s 92 tok/s 56 tok/s | ~872 ms ~875 ms ~882 ms | |
- | Liquid D1-VL 3B | 3B | INT4 Q8 FP16 | 130 tok/s 92 tok/s 56 tok/s | ~872 ms ~875 ms ~882 ms | |
- | Liquid LFM2-VL 3B D1 | 3B | INT4 Q8 FP16 | 130 tok/s 92 tok/s 56 tok/s | ~872 ms ~875 ms ~882 ms | |
- | Qwen2.5-3B | 3B | INT4 Q8 FP16 | 130 tok/s 92 tok/s 56 tok/s | ~872 ms ~875 ms ~882 ms | |
- | LFM2.5 24B A2B | 24B (2.5B active) | INT4 | 116 tok/s | ~1.0s | |
- | FLUX.2 Klein 4B | 4B | INT4 Q8 FP16 | 111 tok/s 76 tok/s 45 tok/s | ~1.1s ~1.1s ~1.2s | |
- | FrogNano 4B | 4B | INT4 Q8 FP16 | 111 tok/s 76 tok/s 45 tok/s | ~1.1s ~1.1s ~1.2s | |
- | Mage-VL Cowork | 4B | INT4 Q8 FP16 | 111 tok/s 76 tok/s 45 tok/s | ~1.1s ~1.1s ~1.2s | |
- | Spark X2.5 4B | 4B | INT4 Q8 FP16 | 111 tok/s 76 tok/s 45 tok/s | ~1.1s ~1.1s ~1.2s | |
- | ERNIE-4.5-21B-A3B | 21B (3B active) | INT4 | 110 tok/s | ~1.2s | |
- | ERNIE-4.5-21B-A3B-Base | 21B (3B active) | INT4 | 110 tok/s | ~1.2s | |
- | EmbeddingGemma 2 | 2B | INT4 Q8 FP16 | 107 tok/s 89 tok/s 63 tok/s | ~610 ms ~612 ms ~617 ms | |
- | ERNIE-4.5-VL-28B-A3B | 28B (3B active) | INT4 | 101 tok/s | ~1.3s | |
- | ERNIE-4.5-VL-28B-A3B-Base | 28B (3B active) | INT4 | 101 tok/s | ~1.3s | |
- | CogVideoX 1.5 5B | 5B | INT4 Q8 FP16 | 97 tok/s 64 tok/s 37 tok/s | ~1.4s ~1.4s ~1.4s | |
- | CogVideoX 5B | 5B | INT4 Q8 FP16 | 97 tok/s 64 tok/s 37 tok/s | ~1.4s ~1.4s ~1.4s | |
- | Wan 2.2 TI2V 5B | 5B | INT4 Q8 FP16 | 97 tok/s 64 tok/s 37 tok/s | ~1.4s ~1.4s ~1.4s | |
- | Phi-2 | 2.7B | INT4 Q8 FP16 | 96 tok/s 77 tok/s 52 tok/s | ~796 ms ~799 ms ~805 ms | |
- | MaLLaM-3B | 3B | INT4 Q8 FP16 | 91 tok/s 73 tok/s 48 tok/s | ~876 ms ~878 ms ~885 ms | |
- | SmolLM3 3B | 3B | INT4 Q8 FP16 | 91 tok/s 73 tok/s 48 tok/s | ~876 ms ~878 ms ~885 ms | |
- | Falcon-7B | 7B | INT4 Q8 FP16 | 81 tok/s 51 tok/s 27 tok/s | ~1.9s ~1.9s ~2.1s | |
- | AuraFlow v0.2 | 6.8B | INT4 Q8 FP16 | 79 tok/s 51 tok/s 27 tok/s | ~1.9s ~1.9s ~2.1s | |
- | AuraFlow v0.3 | 6.8B | INT4 Q8 FP16 | 79 tok/s 51 tok/s 27 tok/s | ~1.9s ~1.9s ~2.1s | |
- | Falcon3-7B | 7B | INT4 Q8 FP16 | 77 tok/s 50 tok/s 25 tok/s | ~1.9s ~1.9s ~2.3s | |
- | Hy-MT2 7B | 7B | INT4 Q8 FP16 | 77 tok/s 50 tok/s 25 tok/s | ~1.9s ~1.9s ~2.3s | |
- | Mistral-7B-v0.1 | 7.3B | INT4 Q8 FP16 | 75 tok/s 48 tok/s 24 tok/s | ~2.0s ~2.0s ~2.4s | |
- | Youtu Parsing Omni | 8B | INT4 Q8 | 72 tok/s 45 tok/s | ~2.2s ~2.2s | |
- | Stable Diffusion 3.5 Large | 8.1B | INT4 Q8 | 70 tok/s 44 tok/s | ~2.2s ~2.2s | |
- | Stable Diffusion 3.5 Large Turbo | 8.1B | INT4 Q8 | 70 tok/s 44 tok/s | ~2.2s ~2.2s | |
- | FLUX.2 Klein 9B | 9B | INT4 Q8 | 64 tok/s 40 tok/s | ~2.5s ~2.5s | |
- | LensVLM 9B | 9B | INT4 Q8 | 64 tok/s 40 tok/s | ~2.5s ~2.5s | |
- | MiMo V2.6 Distill Qwen 9B | 9B | INT4 Q8 | 64 tok/s 40 tok/s | ~2.5s ~2.5s | |
- | ChatGLM3-6B-32K | 6B | INT4 Q8 FP16 | 63 tok/s 46 tok/s 27 tok/s | ~1.7s ~1.7s ~1.8s | |
- | Yi-6B | 6B | INT4 Q8 FP16 | 63 tok/s 46 tok/s 27 tok/s | ~1.7s ~1.7s ~1.8s | |
- | Falcon3-10B | 10B | INT4 Q8 | 59 tok/s 37 tok/s | ~2.7s ~2.8s | |
- | Mochi 1 Preview | 10B | INT4 Q8 | 59 tok/s 37 tok/s | ~2.7s ~2.8s | |
- | Falcon2-11B | 11B | INT4 Q8 | 57 tok/s 35 tok/s | ~3.0s ~3.0s | |
- | Hunyuan Lite | 7B | INT4 Q8 | 57 tok/s 41 tok/s | ~1.9s ~2.0s | |
- | Kimi-VL-A3B-Instruct | 16B (3B active) | INT4 | 57 tok/s | ~1.1s | |
- | OLMo 3 7B Base | 7B | INT4 Q8 | 57 tok/s 41 tok/s | ~1.9s ~2.0s | |
- | SEA-LION-7B | 7.1B | INT4 Q8 | 56 tok/s 40 tok/s | ~2.0s ~2.0s | |
- | SEA-LION-7B-Instruct | 7.1B | INT4 Q8 | 56 tok/s 40 tok/s | ~2.0s ~2.0s | |
- | FLUX.1 Canny Dev | 11.9B | INT4 Q8 | 52 tok/s 30 tok/s | ~3.3s ~3.6s | |
- | FLUX.1 Depth Dev | 11.9B | INT4 Q8 | 52 tok/s 30 tok/s | ~3.3s ~3.6s | |
- | FLUX.1 Dev | 11.9B | INT4 Q8 | 52 tok/s 30 tok/s | ~3.3s ~3.6s | |
- | FLUX.1 Fill Dev | 11.9B | INT4 Q8 | 52 tok/s 30 tok/s | ~3.3s ~3.6s | |
- | FLUX.1 Schnell | 11.9B | INT4 Q8 | 52 tok/s 30 tok/s | ~3.3s ~3.6s | |
- | Sahabat-AI-Llama3-8B-Instruct | 8B | INT4 Q8 | 52 tok/s 37 tok/s | ~2.2s ~2.2s | |
- | Typhoon-2-8B | 8B | INT4 Q8 | 52 tok/s 37 tok/s | ~2.2s ~2.2s | |
- | HunyuanVideo 1.5 720P T2V | 13B | INT4 Q8 | 48 tok/s 28 tok/s | ~3.6s ~3.9s | |
- | GLM-4-9B | 9B | INT4 Q8 | 47 tok/s 32 tok/s | ~2.5s ~2.7s | |
- | GLM-4-9B-Chat | 9B | INT4 Q8 | 47 tok/s 32 tok/s | ~2.5s ~2.7s | |
- | GLM-4-9B-Chat-1M | 9B | INT4 Q8 | 47 tok/s 32 tok/s | ~2.5s ~2.7s | |
- | Sahabat-AI-Gemma2-9B | 9.2B | INT4 Q8 | 47 tok/s 31 tok/s | ~2.5s ~2.8s | |
- | Sahabat-AI-Gemma2-9B-Instruct | 9.2B | INT4 Q8 | 47 tok/s 31 tok/s | ~2.5s ~2.8s | |
- | Yi-9B | 9B | INT4 Q8 | 47 tok/s 32 tok/s | ~2.5s ~2.7s | |
- | Wan 2.1 I2V 14B 720P | 14B | INT4 Q8 | 45 tok/s 25 tok/s | ~3.8s ~4.5s | |
- | Wan 2.1 T2V 14B | 14B | INT4 Q8 | 45 tok/s 25 tok/s | ~3.8s ~4.5s | |
- | Wan 2.2 T2V A14B | 14B | INT4 Q8 | 45 tok/s 25 tok/s | ~3.8s ~4.5s | |
- | FLUX.2 Dev | 15B | INT4 Q8 | 43 tok/s 23 tok/s | ~4.1s ~4.8s | |
- | GreenMind-14B-R1 | 14B | INT4 | 34 tok/s | ~3.8s | |
- | Arete 27B | 27B | INT4 | 23 tok/s | ~8.5s | |
- | AREX-2 | 27B | INT4 | 23 tok/s | ~8.5s | |
- | PPLX Decider v1 27B | 27B | INT4 | 23 tok/s | ~8.5s | |
- | PPLX Decider v1.1 27B | 27B | INT4 | 23 tok/s | ~8.5s | |
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 6900 XT (16GB).
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 512 GB/s aggregate bandwidth, batch size 1 inference operates in a memory-bandwidth bound regime. Generates approximately 114 tok/s on an 8B Q4 model and 13 tok/s on a 70B Q4 model.
Frequently Asked Questions
©2025 ApX Machine Learning