AMD RX 7600 XT (16GB)
The AMD RX 7600 XT (16GB) provides 16 GB of memory with 288 GB/s bandwidth, supporting local inference via ROCm and Vulkan acceleration.
Memory
16 GB
Usable Memory Ceiling
16 GB
Bandwidth
288 GB/s
Max Inference Class
14B Models (Q4)
TDP
190W
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 7600 XT (16GB)
Inference throughput, memory compatibility, and generation speeds for open-weights LLMs on AMD RX 7600 XT (16GB).
Sort by:
Context:
KV Cache:
GPUs:
| Rank | Model | Parameters | Precision | TPS (Approx.) | TTFT | Can Run |
|---|---|---|---|---|---|---|
#48 | Qwen 3.8 27B | 27B | INT4 | 14 tok/s | ~8.8s | |
#93 | Qwen3.5-27B | 27B | INT4 | 14 tok/s | ~8.8s | |
#111 | MiMo V2 Flash | 15B (309B active) | INT4 | 1 tok/s | ~88.5s | |
#112 | Phi-4 Reasoning Plus | 14B | INT4 | 20 tok/s | ~3.9s | |
#117 | Gemma 4 26B A4B | 25.2B (3.8B active) | INT4 | 64 tok/s | ~1.5s | |
#125 | Qwen3.5-9B | 9B | INT4 Q8 | 40 tok/s 24 tok/s | ~2.5s ~2.6s | |
#128 | K2 Horizon 7B | 7B | INT4 Q8 FP16 | 49 tok/s 30 tok/s 15 tok/s | ~2.0s ~2.0s ~2.4s | |
#135 | Gemma 4 12B | 11.95B | INT4 Q8 | 23 tok/s 14 tok/s | ~3.4s ~4.0s | |
#140 | Qwen3.5-4B | 4B | INT4 Q8 FP16 | 75 tok/s 48 tok/s 27 tok/s | ~1.2s ~1.2s ~1.2s | |
#143 | GPT-OSS 20B | 21B (3.6B active) | INT4 | 29 tok/s | ~1.5s | |
#144 | GLM-4V | 9B | INT4 Q8 | 29 tok/s 19 tok/s | ~2.6s ~2.8s | |
#150 | NVIDIA Nemotron 3 Nano 30B-A3B | 3.5B (30B active) | INT4 Q8 FP16 | 13 tok/s 8 tok/s 4 tok/s | ~8.0s ~8.1s ~8.2s | |
#158 | Granite 4.2 8B | 8B | INT4 Q8 | 44 tok/s 27 tok/s | ~2.3s ~2.3s | |
#159 | Gemma 4 E4B | 8B | INT4 Q8 | 44 tok/s 27 tok/s | ~2.3s ~2.3s | |
#166 | Phi-4 | 14B | INT4 Q8 | 27 tok/s 14 tok/s | ~3.9s ~4.6s | |
#167 | Gemma 3 27B | 27B | INT4 | 14 tok/s | ~8.8s | |
#178 | OLMo 3 7B Think | 7B | INT4 Q8 | 35 tok/s 24 tok/s | ~2.0s ~2.0s | |
#179 | DeepSeek-R1 14B | 14B | INT4 Q8 | 28 tok/s 15 tok/s | ~3.9s ~4.6s | |
#183 | Ministral 3 14B | 14B | INT4 | 20 tok/s | ~3.9s | |
#186 | Gemma 3 12B | 12B | INT4 Q8 | 31 tok/s 18 tok/s | ~3.4s ~3.7s | |
#188 | Mistral-Small-2501 | 24B | INT4 | 16 tok/s | ~7.2s | |
#189 | Ministral 3 8B | 8B | INT4 Q8 | 32 tok/s 22 tok/s | ~2.3s ~2.3s | |
#191 | MiniCPM5-2B | 2B | INT4 Q8 FP16 | 115 tok/s 81 tok/s 49 tok/s | ~623 ms ~627 ms ~635 ms | |
#192 | Qwen3.5-2B | 2B | INT4 Q8 FP16 | 115 tok/s 81 tok/s 49 tok/s | ~623 ms ~627 ms ~635 ms | |
#193 | Gemma 2 27B | 27B | INT4 | 14 tok/s | ~8.8s | |
#194 | Qwen2.5-14B | 14B | INT4 Q8 | 27 tok/s 14 tok/s | ~3.9s ~4.6s | |
#200 | Gemma 4 E2B | 5.1B | INT4 Q8 FP16 | 63 tok/s 40 tok/s 22 tok/s | ~1.5s ~1.5s ~1.5s | |
#202 | DeepSeek-R1 8B | 8B | INT4 Q8 | 46 tok/s 27 tok/s | ~2.3s ~2.3s | |
#204 | Qwen3-4B | 4B | INT4 Q8 FP16 | 75 tok/s 48 tok/s 27 tok/s | ~1.2s ~1.2s ~1.2s | |
#205 | Ministral 3 3B | 3B | INT4 Q8 FP16 | 60 tok/s 46 tok/s 29 tok/s | ~900 ms ~905 ms ~918 ms | |
#207 | Gemma 2 9B | 9B | INT4 Q8 | 40 tok/s 24 tok/s | ~2.5s ~2.6s | |
#208 | Qwen3.5-0.8B | 0.8B | INT4 Q8 FP16 | 179 tok/s 142 tok/s 97 tok/s | ~257 ms ~259 ms ~262 ms | |
#209 | Qwen3-14B | 14B | INT4 Q8 | 27 tok/s 14 tok/s | ~3.9s ~4.6s | |
#210 | Gemma 3 4B | 4B | INT4 Q8 FP16 | 75 tok/s 48 tok/s 27 tok/s | ~1.2s ~1.2s ~1.2s | |
#211 | Qwen3-8B | 8B | INT4 Q8 | 44 tok/s 27 tok/s | ~2.3s ~2.3s | |
#213 | DeepSeek-R1 7B | 7B | INT4 Q8 FP16 | 51 tok/s 31 tok/s 15 tok/s | ~2.0s ~2.0s ~2.2s | |
#214 | Qwen3-1.7B | 1.7B | INT4 Q8 FP16 | 126 tok/s 91 tok/s 56 tok/s | ~534 ms ~537 ms ~544 ms | |
#215 | Llama 3.1 8B | 8B | INT4 Q8 | 44 tok/s 27 tok/s | ~2.3s ~2.3s | |
#216 | Gemma 3 270M | 0.27B | INT4 Q8 FP16 | 212 tok/s 194 tok/s 160 tok/s | ~90 ms ~90 ms ~92 ms | |
#218 | Qwen3-0.6B | 0.6B | INT4 Q8 FP16 | 198 tok/s 163 tok/s 116 tok/s | ~192 ms ~193 ms ~195 ms | |
#219 | Llama 3 8B | 8B | INT4 Q8 | 44 tok/s 27 tok/s | ~2.3s ~2.3s | |
#221 | Phi-4-Mini | 3.8B | INT4 Q8 FP16 | 78 tok/s 50 tok/s 28 tok/s | ~1.1s ~1.1s ~1.1s | |
#223 | Qwen2.5-7B | 7B | INT4 Q8 FP16 | 49 tok/s 30 tok/s 15 tok/s | ~2.0s ~2.0s ~2.4s | |
#224 | Ministral-8B-2410 | 8B | INT4 Q8 | 44 tok/s 27 tok/s | ~2.3s ~2.3s | |
#225 | DeepSeek-R1 1.5B | 1.5B | INT4 Q8 FP16 | 135 tok/s 98 tok/s 61 tok/s | ~473 ms ~476 ms ~482 ms | |
#226 | Llama 3.2 3B | 3B | INT4 Q8 FP16 | 91 tok/s 61 tok/s 35 tok/s | ~895 ms ~900 ms ~912 ms | |
#228 | Phi-3-mini | 3.8B | INT4 Q8 FP16 | 78 tok/s 50 tok/s 28 tok/s | ~1.1s ~1.1s ~1.1s | |
#229 | Gemma 3n E2B IT | 6B (2B active) | INT4 Q8 FP16 | 60 tok/s 51 tok/s 34 tok/s | ~673 ms ~676 ms ~742 ms | |
#230 | Mistral-7B-Instruct-v0.1 | 7.3B | INT4 Q8 FP16 | 48 tok/s 29 tok/s 14 tok/s | ~2.1s ~2.1s ~2.5s | |
#231 | Llama 3.2 1B | 1B | INT4 Q8 FP16 | 162 tok/s 125 tok/s 83 tok/s | ~325 ms ~327 ms ~331 ms | |
#232 | Gemma 2 2B | 2B | INT4 Q8 FP16 | 115 tok/s 81 tok/s 49 tok/s | ~623 ms ~627 ms ~635 ms | |
#233 | Phi-3-medium | 14B | INT4 Q8 | 27 tok/s 14 tok/s | ~3.9s ~4.6s | |
#234 | OLMo 3 7B Instruct | 7B | INT4 Q8 | 35 tok/s 24 tok/s | ~2.0s ~2.0s | |
#236 | Qwen2-7B | 7B | INT4 Q8 FP16 | 49 tok/s 30 tok/s 15 tok/s | ~2.0s ~2.0s ~2.4s | |
#237 | Phi-3-small | 7B | INT4 Q8 FP16 | 49 tok/s 30 tok/s 15 tok/s | ~2.0s ~2.0s ~2.4s | |
#238 | Gemma 3 1B | 1B | INT4 Q8 FP16 | 162 tok/s 125 tok/s 83 tok/s | ~325 ms ~327 ms ~331 ms | |
#239 | Mistral-7B-Instruct-v0.2 | 7.3B | INT4 Q8 FP16 | 48 tok/s 29 tok/s 14 tok/s | ~2.1s ~2.1s ~2.5s | |
#241 | Gemma 1 7B | 7B | INT4 Q8 | 35 tok/s 24 tok/s | ~2.0s ~2.0s | |
#242 | Gemma 1 2B | 2B | INT4 Q8 FP16 | 123 tok/s 84 tok/s 50 tok/s | ~622 ms ~626 ms ~634 ms | |
#243 | ChatGLM3-6B | 6B | INT4 Q8 FP16 | 39 tok/s 28 tok/s 16 tok/s | ~1.7s ~1.7s ~1.9s | |
#244 | ChatGLM2-6B | 6B | INT4 Q8 FP16 | 39 tok/s 28 tok/s 16 tok/s | ~1.7s ~1.7s ~1.9s | |
#245 | ChatGLM-6B | 6B | INT4 Q8 FP16 | 39 tok/s 28 tok/s 16 tok/s | ~1.7s ~1.7s ~1.9s | |
Unranked Models (Sorted by Speed) | ||||||
- | DINOv3 ViT-L/16 | 0.3B | INT4 Q8 FP16 | 235 tok/s 208 tok/s 166 tok/s | ~99 ms ~99 ms ~101 ms | |
- | Qwen2-0.5B | 0.5B | INT4 Q8 FP16 | 210 tok/s 176 tok/s 129 tok/s | ~160 ms ~161 ms ~163 ms | |
- | Qwen2.5-0.5B | 0.5B | INT4 Q8 FP16 | 210 tok/s 176 tok/s 129 tok/s | ~160 ms ~161 ms ~163 ms | |
- | ERNIE-4.5-0.3B | 0.3B | INT4 Q8 FP16 | 205 tok/s 186 tok/s 151 tok/s | ~99 ms ~100 ms ~101 ms | |
- | ERNIE-4.5-0.3B-Base | 0.3B | INT4 Q8 FP16 | 205 tok/s 186 tok/s 151 tok/s | ~99 ms ~100 ms ~101 ms | |
- | Liquid D1-Omni 600M | 0.6B | INT4 Q8 FP16 | 198 tok/s 163 tok/s 116 tok/s | ~192 ms ~193 ms ~195 ms | |
- | PixArt-α XL 2 1024-MS | 0.61B | INT4 Q8 FP16 | 197 tok/s 162 tok/s 115 tok/s | ~195 ms ~196 ms ~198 ms | |
- | PixArt-Σ XL 2 1024-MS | 0.61B | INT4 Q8 FP16 | 197 tok/s 162 tok/s 115 tok/s | ~195 ms ~196 ms ~198 ms | |
- | Nemotron 3.5 Parse | 0.63B | INT4 Q8 FP16 | 195 tok/s 159 tok/s 113 tok/s | ~202 ms ~203 ms ~206 ms | |
- | SD 2.1 Turbo | 0.86B | INT4 Q8 FP16 | 174 tok/s 136 tok/s 92 tok/s | ~277 ms ~278 ms ~282 ms | |
- | Stable Diffusion 1.4 | 0.86B | INT4 Q8 FP16 | 174 tok/s 136 tok/s 92 tok/s | ~277 ms ~278 ms ~282 ms | |
- | Stable Diffusion 2.1 | 0.86B | INT4 Q8 FP16 | 174 tok/s 136 tok/s 92 tok/s | ~277 ms ~278 ms ~282 ms | |
- | Falcon-1B | 1B | INT4 Q8 FP16 | 172 tok/s 130 tok/s 85 tok/s | ~325 ms ~327 ms ~331 ms | |
- | Falcon3-1B | 1B | INT4 Q8 FP16 | 162 tok/s 125 tok/s 83 tok/s | ~325 ms ~327 ms ~331 ms | |
- | MiniCPM-V 4.7 1B | 1B | INT4 Q8 FP16 | 162 tok/s 125 tok/s 83 tok/s | ~325 ms ~327 ms ~331 ms | |
- | Kandinsky 2.2 Decoder | 1.22B | INT4 Q8 FP16 | 149 tok/s 112 tok/s 72 tok/s | ~390 ms ~393 ms ~398 ms | |
- | Wan 2.1 T2V 1.3B | 1.3B | INT4 Q8 FP16 | 145 tok/s 108 tok/s 68 tok/s | ~413 ms ~415 ms ~420 ms | |
- | Qwen2-1.5B | 1.5B | INT4 Q8 FP16 | 135 tok/s 98 tok/s 61 tok/s | ~473 ms ~476 ms ~482 ms | |
- | Qwen2.5-1.5B | 1.5B | INT4 Q8 FP16 | 135 tok/s 98 tok/s 61 tok/s | ~473 ms ~476 ms ~482 ms | |
- | SVD Image-to-Video XT | 1.5B | INT4 Q8 FP16 | 135 tok/s 98 tok/s 61 tok/s | ~473 ms ~476 ms ~482 ms | |
- | SVD Image-to-Video XT 1.1 | 1.5B | INT4 Q8 FP16 | 135 tok/s 98 tok/s 61 tok/s | ~473 ms ~476 ms ~482 ms | |
- | LFM3 1.7B | 1.7B | INT4 Q8 FP16 | 126 tok/s 91 tok/s 56 tok/s | ~534 ms ~537 ms ~544 ms | |
- | LFM3 1.7B Base | 1.7B | INT4 Q8 FP16 | 126 tok/s 91 tok/s 56 tok/s | ~534 ms ~537 ms ~544 ms | |
- | Spark X2.5 1.7B | 1.7B | INT4 Q8 FP16 | 126 tok/s 91 tok/s 56 tok/s | ~534 ms ~537 ms ~544 ms | |
- | Hy-MT2 1.8B | 1.8B | INT4 Q8 FP16 | 122 tok/s 87 tok/s 53 tok/s | ~562 ms ~565 ms ~572 ms | |
- | CogVideoX 2B | 2B | INT4 Q8 FP16 | 115 tok/s 81 tok/s 49 tok/s | ~623 ms ~627 ms ~635 ms | |
- | LFM3 Audio 2B | 2B | INT4 Q8 FP16 | 115 tok/s 81 tok/s 49 tok/s | ~623 ms ~627 ms ~635 ms | |
- | LFM3 Omni 2B | 2B | INT4 Q8 FP16 | 115 tok/s 81 tok/s 49 tok/s | ~623 ms ~627 ms ~635 ms | |
- | LFM3 VL 2B | 2B | INT4 Q8 FP16 | 115 tok/s 81 tok/s 49 tok/s | ~623 ms ~627 ms ~635 ms | |
- | Liquid D1 2B | 2B | INT4 Q8 FP16 | 115 tok/s 81 tok/s 49 tok/s | ~623 ms ~627 ms ~635 ms | |
- | LTX-Video 0.9.1 | 2B | INT4 Q8 FP16 | 115 tok/s 81 tok/s 49 tok/s | ~623 ms ~627 ms ~635 ms | |
- | Moondream 3.1 | 9B (2B active) | INT4 Q8 | 115 tok/s 81 tok/s | ~701 ms ~705 ms | |
- | Stable Diffusion 3 Medium | 2B | INT4 Q8 FP16 | 115 tok/s 81 tok/s 49 tok/s | ~623 ms ~627 ms ~635 ms | |
- | Kandinsky 3.0 | 2.1B | INT4 Q8 FP16 | 112 tok/s 78 tok/s 47 tok/s | ~650 ms ~654 ms ~663 ms | |
- | LTX-2 | 2.2B | INT4 Q8 FP16 | 109 tok/s 76 tok/s 45 tok/s | ~677 ms ~681 ms ~690 ms | |
- | SDXL 1.0 Refiner | 2.31B | INT4 Q8 FP16 | 106 tok/s 73 tok/s 43 tok/s | ~707 ms ~711 ms ~721 ms | |
- | Stable Diffusion 3.5 Medium | 2.5B | INT4 Q8 FP16 | 102 tok/s 69 tok/s 41 tok/s | ~759 ms ~763 ms ~774 ms | |
- | SDXL 1.0 Base | 2.56B | INT4 Q8 FP16 | 100 tok/s 68 tok/s 40 tok/s | ~775 ms ~780 ms ~790 ms | |
- | SDXL Turbo | 2.56B | INT4 Q8 FP16 | 100 tok/s 68 tok/s 40 tok/s | ~775 ms ~780 ms ~790 ms | |
- | Falcon-3B | 3B | INT4 Q8 FP16 | 97 tok/s 63 tok/s 35 tok/s | ~894 ms ~900 ms ~912 ms | |
- | CroissantLLM Base | 1.3B | INT4 Q8 FP16 | 95 tok/s 79 tok/s 56 tok/s | ~416 ms ~418 ms ~424 ms | |
- | Phi-1 | 1.3B | INT4 Q8 FP16 | 95 tok/s 79 tok/s 56 tok/s | ~416 ms ~418 ms ~424 ms | |
- | Phi-1.5 | 1.3B | INT4 Q8 FP16 | 95 tok/s 79 tok/s 56 tok/s | ~416 ms ~418 ms ~424 ms | |
- | Mellum 2.1 12B A2.5B Thinking | 12B (2.5B active) | INT4 Q8 | 93 tok/s 62 tok/s | ~874 ms ~954 ms | |
- | DeepSeek-R1 3B | 3B | INT4 Q8 FP16 | 92 tok/s 61 tok/s 35 tok/s | ~894 ms ~900 ms ~912 ms | |
- | Falcon3-3B | 3B | INT4 Q8 FP16 | 91 tok/s 61 tok/s 35 tok/s | ~895 ms ~900 ms ~912 ms | |
- | LFM2-VL 3B | 3B | INT4 Q8 FP16 | 91 tok/s 61 tok/s 35 tok/s | ~895 ms ~900 ms ~912 ms | |
- | Liquid D1 3B | 3B | INT4 Q8 FP16 | 91 tok/s 61 tok/s 35 tok/s | ~895 ms ~900 ms ~912 ms | |
- | Liquid D1-VL 3B | 3B | INT4 Q8 FP16 | 91 tok/s 61 tok/s 35 tok/s | ~895 ms ~900 ms ~912 ms | |
- | Liquid LFM2-VL 3B D1 | 3B | INT4 Q8 FP16 | 91 tok/s 61 tok/s 35 tok/s | ~895 ms ~900 ms ~912 ms | |
- | Qwen2.5-3B | 3B | INT4 Q8 FP16 | 91 tok/s 61 tok/s 35 tok/s | ~895 ms ~900 ms ~912 ms | |
- | LFM2.5 24B A2B | 24B (2.5B active) | INT4 | 81 tok/s | ~1.1s | |
- | ERNIE-4.5-21B-A3B | 21B (3B active) | INT4 | 75 tok/s | ~1.2s | |
- | ERNIE-4.5-21B-A3B-Base | 21B (3B active) | INT4 | 75 tok/s | ~1.2s | |
- | FLUX.2 Klein 4B | 4B | INT4 Q8 FP16 | 75 tok/s 48 tok/s 27 tok/s | ~1.2s ~1.2s ~1.2s | |
- | FrogNano 4B | 4B | INT4 Q8 FP16 | 75 tok/s 48 tok/s 27 tok/s | ~1.2s ~1.2s ~1.2s | |
- | Mage-VL Cowork | 4B | INT4 Q8 FP16 | 75 tok/s 48 tok/s 27 tok/s | ~1.2s ~1.2s ~1.2s | |
- | Spark X2.5 4B | 4B | INT4 Q8 FP16 | 75 tok/s 48 tok/s 27 tok/s | ~1.2s ~1.2s ~1.2s | |
- | EmbeddingGemma 2 | 2B | INT4 Q8 FP16 | 72 tok/s 58 tok/s 39 tok/s | ~628 ms ~632 ms ~640 ms | |
- | ERNIE-4.5-VL-28B-A3B | 28B (3B active) | INT4 | 69 tok/s | ~1.4s | |
- | ERNIE-4.5-VL-28B-A3B-Base | 28B (3B active) | INT4 | 69 tok/s | ~1.4s | |
- | CogVideoX 1.5 5B | 5B | INT4 Q8 FP16 | 64 tok/s 40 tok/s 22 tok/s | ~1.4s ~1.5s ~1.5s | |
- | CogVideoX 5B | 5B | INT4 Q8 FP16 | 64 tok/s 40 tok/s 22 tok/s | ~1.4s ~1.5s ~1.5s | |
- | Wan 2.2 TI2V 5B | 5B | INT4 Q8 FP16 | 64 tok/s 40 tok/s 22 tok/s | ~1.4s ~1.5s ~1.5s | |
- | Phi-2 | 2.7B | INT4 Q8 FP16 | 63 tok/s 49 tok/s 32 tok/s | ~819 ms ~823 ms ~834 ms | |
- | MaLLaM-3B | 3B | INT4 Q8 FP16 | 60 tok/s 46 tok/s 29 tok/s | ~900 ms ~905 ms ~918 ms | |
- | SmolLM3 3B | 3B | INT4 Q8 FP16 | 60 tok/s 46 tok/s 29 tok/s | ~900 ms ~905 ms ~918 ms | |
- | Falcon-7B | 7B | INT4 Q8 FP16 | 52 tok/s 31 tok/s 16 tok/s | ~2.0s ~2.0s ~2.2s | |
- | AuraFlow v0.2 | 6.8B | INT4 Q8 FP16 | 51 tok/s 31 tok/s 16 tok/s | ~1.9s ~1.9s ~2.1s | |
- | AuraFlow v0.3 | 6.8B | INT4 Q8 FP16 | 51 tok/s 31 tok/s 16 tok/s | ~1.9s ~1.9s ~2.1s | |
- | Falcon3-7B | 7B | INT4 Q8 FP16 | 49 tok/s 30 tok/s 15 tok/s | ~2.0s ~2.0s ~2.4s | |
- | Hy-MT2 7B | 7B | INT4 Q8 FP16 | 49 tok/s 30 tok/s 15 tok/s | ~2.0s ~2.0s ~2.4s | |
- | Mistral-7B-v0.1 | 7.3B | INT4 Q8 FP16 | 48 tok/s 29 tok/s 14 tok/s | ~2.1s ~2.1s ~2.5s | |
- | Youtu Parsing Omni | 8B | INT4 Q8 | 46 tok/s 27 tok/s | ~2.3s ~2.3s | |
- | Stable Diffusion 3.5 Large | 8.1B | INT4 Q8 | 44 tok/s 26 tok/s | ~2.3s ~2.3s | |
- | Stable Diffusion 3.5 Large Turbo | 8.1B | INT4 Q8 | 44 tok/s 26 tok/s | ~2.3s ~2.3s | |
- | FLUX.2 Klein 9B | 9B | INT4 Q8 | 40 tok/s 24 tok/s | ~2.5s ~2.6s | |
- | LensVLM 9B | 9B | INT4 Q8 | 40 tok/s 24 tok/s | ~2.5s ~2.6s | |
- | MiMo V2.6 Distill Qwen 9B | 9B | INT4 Q8 | 40 tok/s 24 tok/s | ~2.5s ~2.6s | |
- | ChatGLM3-6B-32K | 6B | INT4 Q8 FP16 | 39 tok/s 28 tok/s 16 tok/s | ~1.7s ~1.7s ~1.9s | |
- | Yi-6B | 6B | INT4 Q8 FP16 | 39 tok/s 28 tok/s 16 tok/s | ~1.7s ~1.7s ~1.9s | |
- | Falcon3-10B | 10B | INT4 Q8 | 37 tok/s 22 tok/s | ~2.8s ~2.8s | |
- | Mochi 1 Preview | 10B | INT4 Q8 | 37 tok/s 22 tok/s | ~2.8s ~2.8s | |
- | Falcon2-11B | 11B | INT4 Q8 | 35 tok/s 20 tok/s | ~3.1s ~3.1s | |
- | Hunyuan Lite | 7B | INT4 Q8 | 35 tok/s 24 tok/s | ~2.0s ~2.0s | |
- | Kimi-VL-A3B-Instruct | 16B (3B active) | INT4 | 35 tok/s | ~1.2s | |
- | OLMo 3 7B Base | 7B | INT4 Q8 | 35 tok/s 24 tok/s | ~2.0s ~2.0s | |
- | SEA-LION-7B | 7.1B | INT4 Q8 | 35 tok/s 24 tok/s | ~2.0s ~2.0s | |
- | SEA-LION-7B-Instruct | 7.1B | INT4 Q8 | 35 tok/s 24 tok/s | ~2.0s ~2.0s | |
- | FLUX.1 Canny Dev | 11.9B | INT4 Q8 | 32 tok/s 18 tok/s | ~3.3s ~3.7s | |
- | FLUX.1 Depth Dev | 11.9B | INT4 Q8 | 32 tok/s 18 tok/s | ~3.3s ~3.7s | |
- | FLUX.1 Dev | 11.9B | INT4 Q8 | 32 tok/s 18 tok/s | ~3.3s ~3.7s | |
- | FLUX.1 Fill Dev | 11.9B | INT4 Q8 | 32 tok/s 18 tok/s | ~3.3s ~3.7s | |
- | FLUX.1 Schnell | 11.9B | INT4 Q8 | 32 tok/s 18 tok/s | ~3.3s ~3.7s | |
- | Sahabat-AI-Llama3-8B-Instruct | 8B | INT4 Q8 | 32 tok/s 22 tok/s | ~2.3s ~2.3s | |
- | Typhoon-2-8B | 8B | INT4 Q8 | 32 tok/s 22 tok/s | ~2.3s ~2.3s | |
- | GLM-4-9B | 9B | INT4 Q8 | 29 tok/s 19 tok/s | ~2.6s ~2.8s | |
- | GLM-4-9B-Chat | 9B | INT4 Q8 | 29 tok/s 19 tok/s | ~2.6s ~2.8s | |
- | GLM-4-9B-Chat-1M | 9B | INT4 Q8 | 29 tok/s 19 tok/s | ~2.6s ~2.8s | |
- | HunyuanVideo 1.5 720P T2V | 13B | INT4 Q8 | 29 tok/s 16 tok/s | ~3.6s ~4.0s | |
- | Yi-9B | 9B | INT4 Q8 | 29 tok/s 19 tok/s | ~2.6s ~2.8s | |
- | Sahabat-AI-Gemma2-9B | 9.2B | INT4 Q8 | 28 tok/s 18 tok/s | ~2.6s ~2.8s | |
- | Sahabat-AI-Gemma2-9B-Instruct | 9.2B | INT4 Q8 | 28 tok/s 18 tok/s | ~2.6s ~2.8s | |
- | Wan 2.1 I2V 14B 720P | 14B | INT4 Q8 | 27 tok/s 14 tok/s | ~3.9s ~4.6s | |
- | Wan 2.1 T2V 14B | 14B | INT4 Q8 | 27 tok/s 14 tok/s | ~3.9s ~4.6s | |
- | Wan 2.2 T2V A14B | 14B | INT4 Q8 | 27 tok/s 14 tok/s | ~3.9s ~4.6s | |
- | FLUX.2 Dev | 15B | INT4 Q8 | 26 tok/s 14 tok/s | ~4.2s ~5.0s | |
- | GreenMind-14B-R1 | 14B | INT4 | 20 tok/s | ~3.9s | |
- | Arete 27B | 27B | INT4 | 14 tok/s | ~8.8s | |
- | AREX-2 | 27B | INT4 | 14 tok/s | ~8.8s | |
- | PPLX Decider v1 27B | 27B | INT4 | 14 tok/s | ~8.8s | |
- | PPLX Decider v1.1 27B | 27B | INT4 | 14 tok/s | ~8.8s | |
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 7600 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 288 GB/s aggregate bandwidth, batch size 1 inference operates in a memory-bandwidth bound regime. Generates approximately 64 tok/s on an 8B Q4 model and 8 tok/s on a 70B Q4 model.
Frequently Asked Questions
©2025 ApX Machine Learning