Radeon PRO W7800 (32GB)
The Radeon PRO W7800 (32GB) provides 32 GB of memory with 576 GB/s bandwidth, supporting local inference via ROCm and Vulkan acceleration.
Memory
32 GB
Usable Memory Ceiling
32 GB
Bandwidth
576 GB/s
Max Inference Class
32B Models (Q4)
TDP
260W
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 Radeon PRO W7800 (32GB)
Inference throughput, memory compatibility, and generation speeds for open-weights LLMs on Radeon PRO W7800 (32GB).
Sort by:
Context:
KV Cache:
GPUs:
| Rank | Model | Parameters | Precision | TPS (Approx.) | TTFT | Can Run |
|---|---|---|---|---|---|---|
#36 | Qwen 3.8 27B | 27B | INT4 Q8 | 29 tok/s 16 tok/s | ~3.3s ~3.6s | |
#80 | K2 Horizon MoVA 36B A4B | 36B (4B active) | INT4 | 113 tok/s | ~645 ms | |
#86 | Qwen3.5-27B | 27B | INT4 Q8 | 29 tok/s 16 tok/s | ~3.3s ~3.6s | |
#93 | Sarvam-30B | 32B (2.4B active) | INT4 | 143 tok/s | ~451 ms | |
#99 | Muse Glimmer 30B | 30B | INT4 Q8 | 27 tok/s 14 tok/s | ~3.6s ~4.3s | |
#102 | Phi-4 Reasoning Plus | 14B | INT4 Q8 FP16 | 38 tok/s 26 tok/s 13 tok/s | ~1.7s ~1.7s ~2.1s | |
#103 | Qwen3.6 35B A3B | 35B (3B active) | INT4 | 130 tok/s | ~526 ms | |
#105 | MiMo V2 Flash | 15B (309B active) | INT4 Q8 | 3 tok/s 2 tok/s | ~35.8s ~36.1s | |
#110 | Gemma 4 26B A4B | 25.2B (3.8B active) | INT4 Q8 | 120 tok/s 81 tok/s | ~591 ms ~645 ms | |
#120 | Qwen3.5-35B-A3B | 35B (3B active) | INT4 | 130 tok/s | ~526 ms | |
#121 | Qwen3.5-9B | 9B | INT4 Q8 FP16 | 75 tok/s 46 tok/s 25 tok/s | ~1.1s ~1.1s ~1.1s | |
#127 | K2 Horizon 7B | 7B | INT4 Q8 FP16 | 90 tok/s 57 tok/s 31 tok/s | ~877 ms ~884 ms ~898 ms | |
#130 | Gemma 4 12B | 11.95B | INT4 Q8 FP16 | 44 tok/s 30 tok/s 16 tok/s | ~1.5s ~1.5s ~1.6s | |
#136 | Qwen3.5-4B | 4B | INT4 Q8 FP16 | 132 tok/s 89 tok/s 51 tok/s | ~516 ms ~520 ms ~528 ms | |
#139 | GPT-OSS 20B | 21B (3.6B active) | INT4 Q8 | 60 tok/s 49 tok/s | ~561 ms ~612 ms | |
#140 | GLM-4V | 9B | INT4 Q8 FP16 | 55 tok/s 38 tok/s 22 tok/s | ~1.1s ~1.1s ~1.2s | |
#145 | NVIDIA Nemotron 3 Nano 30B-A3B | 3.5B (30B active) | INT4 Q8 FP16 | 25 tok/s 15 tok/s 8 tok/s | ~3.5s ~3.5s ~3.6s | |
#150 | Qwen3-30B-A3B | 30B (3B active) | INT4 Q8 | 132 tok/s 88 tok/s | ~516 ms ~608 ms | |
#152 | Granite 4.2 8B | 8B | INT4 Q8 FP16 | 82 tok/s 51 tok/s 28 tok/s | ~997 ms ~1.0s ~1.0s | |
#157 | Gemma 4 E4B | 8B | INT4 Q8 FP16 | 82 tok/s 51 tok/s 28 tok/s | ~997 ms ~1.0s ~1.0s | |
#158 | Mistral Large 3 | 41B (675B active) | INT4 | 1 tok/s | ~91.8s | |
#161 | GLM-4 | 32B | INT4 | 20 tok/s | ~3.9s | |
#163 | Gemma 3 27B | 27B | INT4 Q8 | 29 tok/s 16 tok/s | ~3.3s ~3.6s | |
#164 | Phi-4 | 14B | INT4 Q8 FP16 | 52 tok/s 31 tok/s 16 tok/s | ~1.7s ~1.7s ~1.9s | |
#166 | Qwen3-32B | 32B | INT4 | 25 tok/s | ~3.9s | |
#168 | DeepSeek-R1 32B | 32B | INT4 Q8 | 26 tok/s 13 tok/s | ~3.9s ~4.6s | |
#169 | Gemma 4 31B | 30.7B | INT4 Q8 | 26 tok/s 13 tok/s | ~3.7s ~4.4s | |
#171 | Magistral Small | 24B | INT4 Q8 | 25 tok/s 15 tok/s | ~2.9s ~3.2s | |
#172 | Qwen2.5-32B | 32B | INT4 | 25 tok/s | ~3.9s | |
#174 | OLMo 3.1 32B Instruct | 32B | INT4 | 20 tok/s | ~3.9s | |
#176 | DeepSeek-R1 14B | 14B | INT4 Q8 FP16 | 54 tok/s 32 tok/s 16 tok/s | ~1.7s ~1.7s ~1.9s | |
#177 | Ministral 3 14B | 14B | INT4 Q8 FP16 | 38 tok/s 26 tok/s 13 tok/s | ~1.7s ~1.7s ~2.1s | |
#180 | Gemma 3 12B | 12B | INT4 Q8 FP16 | 59 tok/s 36 tok/s 19 tok/s | ~1.5s ~1.5s ~1.5s | |
#184 | Mistral-Small-2501 | 24B | INT4 Q8 | 33 tok/s 18 tok/s | ~2.9s ~3.2s | |
#185 | Ministral 3 8B | 8B | INT4 Q8 FP16 | 60 tok/s 42 tok/s 25 tok/s | ~1.0s ~1.0s ~1.0s | |
#186 | Gemma 2 27B | 27B | INT4 Q8 | 29 tok/s 16 tok/s | ~3.3s ~3.6s | |
#187 | OLMo 3 7B Think | 7B | INT4 Q8 FP16 | 66 tok/s 47 tok/s 28 tok/s | ~881 ms ~887 ms ~902 ms | |
#188 | Qwen3.5-2B | 2B | INT4 Q8 FP16 | 189 tok/s 140 tok/s 89 tok/s | ~277 ms ~279 ms ~283 ms | |
#189 | MiniCPM5-2B | 2B | INT4 Q8 FP16 | 189 tok/s 140 tok/s 89 tok/s | ~277 ms ~279 ms ~283 ms | |
#190 | Qwen2.5-14B | 14B | INT4 Q8 FP16 | 52 tok/s 31 tok/s 16 tok/s | ~1.7s ~1.7s ~1.9s | |
#191 | OLMo 3.1 32B Think | 32B | INT4 | 20 tok/s | ~3.9s | |
#193 | Gemma 4 E2B | 5.1B | INT4 Q8 FP16 | 113 tok/s 74 tok/s 42 tok/s | ~649 ms ~653 ms ~664 ms | |
#195 | Ministral 3 3B | 3B | INT4 Q8 FP16 | 107 tok/s 84 tok/s 56 tok/s | ~399 ms ~402 ms ~408 ms | |
#196 | DeepSeek-R1 8B | 8B | INT4 Q8 FP16 | 84 tok/s 52 tok/s 28 tok/s | ~997 ms ~1.0s ~1.0s | |
#198 | Gemma 2 9B | 9B | INT4 Q8 FP16 | 75 tok/s 46 tok/s 25 tok/s | ~1.1s ~1.1s ~1.1s | |
#199 | Nemotron 3.5 Lightning 30B A3B | 30B (3B active) | INT4 Q8 | 132 tok/s 88 tok/s | ~516 ms ~608 ms | |
#200 | Kimi Linear 48B A3B Instruct | 48B (3B active) | INT4 | 41 tok/s | ~668 ms | |
#201 | Qwen3-4B | 4B | INT4 Q8 FP16 | 132 tok/s 89 tok/s 51 tok/s | ~516 ms ~520 ms ~528 ms | |
#202 | Qwen3-14B | 14B | INT4 Q8 FP16 | 52 tok/s 31 tok/s 16 tok/s | ~1.7s ~1.7s ~1.9s | |
#203 | Gemma 3 4B | 4B | INT4 Q8 FP16 | 132 tok/s 89 tok/s 51 tok/s | ~516 ms ~520 ms ~528 ms | |
#204 | DeepSeek-R1 7B | 7B | INT4 Q8 FP16 | 93 tok/s 58 tok/s 32 tok/s | ~877 ms ~883 ms ~898 ms | |
#205 | OLMo 3 32B Base | 32B | INT4 | 20 tok/s | ~3.9s | |
#206 | Qwen3.5-0.8B | 0.8B | INT4 Q8 FP16 | 267 tok/s 223 tok/s 164 tok/s | ~116 ms ~117 ms ~119 ms | |
#207 | Llama 3.1 8B | 8B | INT4 Q8 FP16 | 82 tok/s 51 tok/s 28 tok/s | ~997 ms ~1.0s ~1.0s | |
#207 | Qwen3-8B | 8B | INT4 Q8 FP16 | 82 tok/s 51 tok/s 28 tok/s | ~997 ms ~1.0s ~1.0s | |
#210 | Nemotron 3.5 Lightning | 30B (3B active) | INT4 | 54 tok/s | ~527 ms | |
#211 | Command R | 35B | INT4 | 18 tok/s | ~4.2s | |
#212 | Llama 3 8B | 8B | INT4 Q8 FP16 | 82 tok/s 51 tok/s 28 tok/s | ~997 ms ~1.0s ~1.0s | |
#213 | Qwen3-1.7B | 1.7B | INT4 Q8 FP16 | 203 tok/s 154 tok/s 101 tok/s | ~238 ms ~239 ms ~243 ms | |
#214 | Gemma 3 270M | 0.27B | INT4 Q8 FP16 | 303 tok/s 283 tok/s 245 tok/s | ~43 ms ~43 ms ~44 ms | |
#216 | Qwen3-0.6B | 0.6B | INT4 Q8 FP16 | 288 tok/s 249 tok/s 191 tok/s | ~88 ms ~88 ms ~89 ms | |
#217 | Phi-4-Mini | 3.8B | INT4 Q8 FP16 | 136 tok/s 92 tok/s 54 tok/s | ~492 ms ~496 ms ~504 ms | |
#218 | Qwen2.5-7B | 7B | INT4 Q8 FP16 | 90 tok/s 57 tok/s 31 tok/s | ~877 ms ~884 ms ~898 ms | |
#219 | Mixtral-8x7B-v0.1 | 46.7B (7B active) | INT4 | 76 tok/s | ~1.1s | |
#220 | Ministral-8B-2410 | 8B | INT4 Q8 FP16 | 82 tok/s 51 tok/s 28 tok/s | ~997 ms ~1.0s ~1.0s | |
#221 | DeepSeek-R1 1.5B | 1.5B | INT4 Q8 FP16 | 215 tok/s 166 tok/s 110 tok/s | ~211 ms ~212 ms ~216 ms | |
#222 | Llama 3.2 3B | 3B | INT4 Q8 FP16 | 155 tok/s 109 tok/s 65 tok/s | ~396 ms ~399 ms ~405 ms | |
#223 | Phi-3-mini | 3.8B | INT4 Q8 FP16 | 136 tok/s 92 tok/s 54 tok/s | ~492 ms ~496 ms ~504 ms | |
#224 | Gemma 3n E2B IT | 6B (2B active) | INT4 Q8 FP16 | 107 tok/s 92 tok/s 67 tok/s | ~299 ms ~301 ms ~305 ms | |
#225 | Gemma 2 2B | 2B | INT4 Q8 FP16 | 189 tok/s 140 tok/s 89 tok/s | ~277 ms ~279 ms ~283 ms | |
#226 | Mistral-7B-Instruct-v0.1 | 7.3B | INT4 Q8 FP16 | 88 tok/s 55 tok/s 30 tok/s | ~912 ms ~919 ms ~934 ms | |
#227 | Llama 3.2 1B | 1B | INT4 Q8 FP16 | 248 tok/s 202 tok/s 143 tok/s | ~146 ms ~147 ms ~149 ms | |
#228 | Phi-3-medium | 14B | INT4 Q8 FP16 | 52 tok/s 31 tok/s 16 tok/s | ~1.7s ~1.7s ~1.9s | |
#229 | Yi-34B | 34B | INT4 | 19 tok/s | ~4.1s | |
#230 | OLMo 3 7B Instruct | 7B | INT4 Q8 FP16 | 66 tok/s 47 tok/s 28 tok/s | ~881 ms ~887 ms ~902 ms | |
#231 | Qwen2-7B | 7B | INT4 Q8 FP16 | 90 tok/s 57 tok/s 31 tok/s | ~877 ms ~884 ms ~898 ms | |
#232 | Phi-3-small | 7B | INT4 Q8 FP16 | 90 tok/s 57 tok/s 31 tok/s | ~877 ms ~884 ms ~898 ms | |
#233 | Mistral-7B-Instruct-v0.2 | 7.3B | INT4 Q8 FP16 | 88 tok/s 55 tok/s 30 tok/s | ~912 ms ~919 ms ~934 ms | |
#234 | Gemma 3 1B | 1B | INT4 Q8 FP16 | 248 tok/s 202 tok/s 143 tok/s | ~146 ms ~147 ms ~149 ms | |
#236 | Gemma 1 7B | 7B | INT4 Q8 FP16 | 66 tok/s 47 tok/s 28 tok/s | ~881 ms ~887 ms ~902 ms | |
#237 | Gemma 1 2B | 2B | INT4 Q8 FP16 | 200 tok/s 146 tok/s 91 tok/s | ~277 ms ~279 ms ~283 ms | |
#238 | ChatGLM3-6B | 6B | INT4 Q8 FP16 | 73 tok/s 53 tok/s 32 tok/s | ~761 ms ~766 ms ~778 ms | |
#239 | ChatGLM2-6B | 6B | INT4 Q8 FP16 | 73 tok/s 53 tok/s 32 tok/s | ~761 ms ~766 ms ~778 ms | |
#240 | ChatGLM-6B | 6B | INT4 Q8 FP16 | 73 tok/s 53 tok/s 32 tok/s | ~761 ms ~766 ms ~778 ms | |
Unranked Models (Sorted by Speed) | ||||||
- | DINOv3 ViT-L/16 | 0.3B | INT4 Q8 FP16 | 325 tok/s 298 tok/s 252 tok/s | ~47 ms ~47 ms ~48 ms | |
- | Qwen2-0.5B | 0.5B | INT4 Q8 FP16 | 300 tok/s 263 tok/s 208 tok/s | ~74 ms ~74 ms ~75 ms | |
- | Qwen2.5-0.5B | 0.5B | INT4 Q8 FP16 | 300 tok/s 263 tok/s 208 tok/s | ~74 ms ~74 ms ~75 ms | |
- | ERNIE-4.5-0.3B | 0.3B | INT4 Q8 FP16 | 295 tok/s 275 tok/s 235 tok/s | ~47 ms ~47 ms ~48 ms | |
- | ERNIE-4.5-0.3B-Base | 0.3B | INT4 Q8 FP16 | 295 tok/s 275 tok/s 235 tok/s | ~47 ms ~47 ms ~48 ms | |
- | Liquid D1-Omni 600M | 0.6B | INT4 Q8 FP16 | 288 tok/s 249 tok/s 191 tok/s | ~88 ms ~88 ms ~89 ms | |
- | Falcon-1B | 1B | INT4 Q8 FP16 | 259 tok/s 209 tok/s 146 tok/s | ~146 ms ~147 ms ~149 ms | |
- | Falcon3-1B | 1B | INT4 Q8 FP16 | 248 tok/s 202 tok/s 143 tok/s | ~146 ms ~147 ms ~149 ms | |
- | MiniCPM-V 4.7 1B | 1B | INT4 Q8 FP16 | 248 tok/s 202 tok/s 143 tok/s | ~146 ms ~147 ms ~149 ms | |
- | Qwen2-1.5B | 1.5B | INT4 Q8 FP16 | 215 tok/s 166 tok/s 110 tok/s | ~211 ms ~212 ms ~216 ms | |
- | Qwen2.5-1.5B | 1.5B | INT4 Q8 FP16 | 215 tok/s 166 tok/s 110 tok/s | ~211 ms ~212 ms ~216 ms | |
- | Spark X2.5 1.7B | 1.7B | INT4 Q8 FP16 | 203 tok/s 154 tok/s 101 tok/s | ~238 ms ~239 ms ~243 ms | |
- | Hy-MT2 1.8B | 1.8B | INT4 Q8 FP16 | 199 tok/s 150 tok/s 97 tok/s | ~250 ms ~252 ms ~255 ms | |
- | Falcon-3B | 3B | INT4 Q8 FP16 | 163 tok/s 112 tok/s 66 tok/s | ~396 ms ~399 ms ~405 ms | |
- | CroissantLLM Base | 1.3B | INT4 Q8 FP16 | 161 tok/s 138 tok/s 101 tok/s | ~186 ms ~188 ms ~190 ms | |
- | Phi-1 | 1.3B | INT4 Q8 FP16 | 161 tok/s 138 tok/s 101 tok/s | ~186 ms ~188 ms ~190 ms | |
- | Phi-1.5 | 1.3B | INT4 Q8 FP16 | 161 tok/s 138 tok/s 101 tok/s | ~186 ms ~188 ms ~190 ms | |
- | DeepSeek-R1 3B | 3B | INT4 Q8 FP16 | 157 tok/s 109 tok/s 66 tok/s | ~396 ms ~399 ms ~405 ms | |
- | Mellum 2.1 12B A2.5B Thinking | 12B (2.5B active) | INT4 Q8 FP16 | 157 tok/s 116 tok/s 73 tok/s | ~387 ms ~389 ms ~394 ms | |
- | Falcon3-3B | 3B | INT4 Q8 FP16 | 155 tok/s 109 tok/s 65 tok/s | ~396 ms ~399 ms ~405 ms | |
- | LFM2-VL 3B | 3B | INT4 Q8 FP16 | 155 tok/s 109 tok/s 65 tok/s | ~396 ms ~399 ms ~405 ms | |
- | Liquid D1 3B | 3B | INT4 Q8 FP16 | 155 tok/s 109 tok/s 65 tok/s | ~396 ms ~399 ms ~405 ms | |
- | Liquid D1-VL 3B | 3B | INT4 Q8 FP16 | 155 tok/s 109 tok/s 65 tok/s | ~396 ms ~399 ms ~405 ms | |
- | Liquid LFM2-VL 3B D1 | 3B | INT4 Q8 FP16 | 155 tok/s 109 tok/s 65 tok/s | ~396 ms ~399 ms ~405 ms | |
- | Qwen2.5-3B | 3B | INT4 Q8 FP16 | 155 tok/s 109 tok/s 65 tok/s | ~396 ms ~399 ms ~405 ms | |
- | LFM2.5 24B A2B | 24B (2.5B active) | INT4 Q8 | 146 tok/s 105 tok/s | ~438 ms ~478 ms | |
- | ERNIE-4.5-21B-A3B | 21B (3B active) | INT4 Q8 | 137 tok/s 100 tok/s | ~483 ms ~486 ms | |
- | ERNIE-4.5-21B-A3B-Base | 21B (3B active) | INT4 Q8 | 137 tok/s 100 tok/s | ~483 ms ~486 ms | |
- | ERNIE-4.5-VL-28B-A3B | 28B (3B active) | INT4 Q8 | 133 tok/s 93 tok/s | ~508 ms ~554 ms | |
- | ERNIE-4.5-VL-28B-A3B-Base | 28B (3B active) | INT4 Q8 | 133 tok/s 93 tok/s | ~508 ms ~554 ms | |
- | FrogNano 4B | 4B | INT4 Q8 FP16 | 132 tok/s 89 tok/s 51 tok/s | ~516 ms ~520 ms ~528 ms | |
- | Hy-Memory 30B A3B | 30B (3B active) | INT4 Q8 | 132 tok/s 88 tok/s | ~516 ms ~608 ms | |
- | Hy-MT2 30B A3B | 30B (3B active) | INT4 Q8 | 132 tok/s 88 tok/s | ~516 ms ~608 ms | |
- | Spark X2.5 4B | 4B | INT4 Q8 FP16 | 132 tok/s 89 tok/s 51 tok/s | ~516 ms ~520 ms ~528 ms | |
- | MiniCPM-V 4.7 35B A3B | 35B (3B active) | INT4 | 130 tok/s | ~526 ms | |
- | EmbeddingGemma 2 | 2B | INT4 Q8 FP16 | 127 tok/s 105 tok/s 73 tok/s | ~280 ms ~281 ms ~285 ms | |
- | Phi-2 | 2.7B | INT4 Q8 FP16 | 113 tok/s 90 tok/s 60 tok/s | ~363 ms ~365 ms ~371 ms | |
- | MaLLaM-3B | 3B | INT4 Q8 FP16 | 107 tok/s 84 tok/s 56 tok/s | ~399 ms ~402 ms ~408 ms | |
- | SmolLM3 3B | 3B | INT4 Q8 FP16 | 107 tok/s 84 tok/s 56 tok/s | ~399 ms ~402 ms ~408 ms | |
- | Falcon-7B | 7B | INT4 Q8 FP16 | 94 tok/s 58 tok/s 32 tok/s | ~877 ms ~883 ms ~897 ms | |
- | Falcon3-7B | 7B | INT4 Q8 FP16 | 90 tok/s 57 tok/s 31 tok/s | ~877 ms ~884 ms ~898 ms | |
- | Hy-MT2 7B | 7B | INT4 Q8 FP16 | 90 tok/s 57 tok/s 31 tok/s | ~877 ms ~884 ms ~898 ms | |
- | Mistral-7B-v0.1 | 7.3B | INT4 Q8 FP16 | 88 tok/s 55 tok/s 30 tok/s | ~912 ms ~919 ms ~934 ms | |
- | Youtu Parsing Omni | 8B | INT4 Q8 FP16 | 84 tok/s 52 tok/s 28 tok/s | ~997 ms ~1.0s ~1.0s | |
- | LensVLM 9B | 9B | INT4 Q8 FP16 | 75 tok/s 46 tok/s 25 tok/s | ~1.1s ~1.1s ~1.1s | |
- | MiMo V2.6 Distill Qwen 9B | 9B | INT4 Q8 FP16 | 75 tok/s 46 tok/s 25 tok/s | ~1.1s ~1.1s ~1.1s | |
- | ChatGLM3-6B-32K | 6B | INT4 Q8 FP16 | 73 tok/s 53 tok/s 32 tok/s | ~761 ms ~766 ms ~778 ms | |
- | Yi-6B | 6B | INT4 Q8 FP16 | 73 tok/s 53 tok/s 32 tok/s | ~761 ms ~766 ms ~778 ms | |
- | Falcon3-10B | 10B | INT4 Q8 FP16 | 69 tok/s 42 tok/s 23 tok/s | ~1.2s ~1.2s ~1.3s | |
- | Kimi-VL-A3B-Instruct | 16B (3B active) | INT4 Q8 | 69 tok/s 60 tok/s | ~471 ms ~473 ms | |
- | Falcon2-11B | 11B | INT4 Q8 FP16 | 66 tok/s 39 tok/s 21 tok/s | ~1.4s ~1.4s ~1.4s | |
- | Hunyuan Lite | 7B | INT4 Q8 FP16 | 66 tok/s 47 tok/s 28 tok/s | ~881 ms ~887 ms ~902 ms | |
- | OLMo 3 7B Base | 7B | INT4 Q8 FP16 | 66 tok/s 47 tok/s 28 tok/s | ~881 ms ~887 ms ~902 ms | |
- | SEA-LION-7B | 7.1B | INT4 Q8 FP16 | 65 tok/s 46 tok/s 28 tok/s | ~893 ms ~899 ms ~914 ms | |
- | SEA-LION-7B-Instruct | 7.1B | INT4 Q8 FP16 | 65 tok/s 46 tok/s 28 tok/s | ~893 ms ~899 ms ~914 ms | |
- | Sahabat-AI-Llama3-8B-Instruct | 8B | INT4 Q8 FP16 | 60 tok/s 42 tok/s 25 tok/s | ~1.0s ~1.0s ~1.0s | |
- | Typhoon-2-8B | 8B | INT4 Q8 FP16 | 60 tok/s 42 tok/s 25 tok/s | ~1.0s ~1.0s ~1.0s | |
- | GLM-4-9B | 9B | INT4 Q8 FP16 | 55 tok/s 38 tok/s 22 tok/s | ~1.1s ~1.1s ~1.2s | |
- | GLM-4-9B-Chat | 9B | INT4 Q8 FP16 | 55 tok/s 38 tok/s 22 tok/s | ~1.1s ~1.1s ~1.2s | |
- | GLM-4-9B-Chat-1M | 9B | INT4 Q8 FP16 | 55 tok/s 38 tok/s 22 tok/s | ~1.1s ~1.1s ~1.2s | |
- | Yi-9B | 9B | INT4 Q8 FP16 | 55 tok/s 38 tok/s 22 tok/s | ~1.1s ~1.1s ~1.2s | |
- | Sahabat-AI-Gemma2-9B | 9.2B | INT4 Q8 FP16 | 54 tok/s 37 tok/s 22 tok/s | ~1.1s ~1.2s ~1.2s | |
- | Sahabat-AI-Gemma2-9B-Instruct | 9.2B | INT4 Q8 FP16 | 54 tok/s 37 tok/s 22 tok/s | ~1.1s ~1.2s ~1.2s | |
- | GreenMind-14B-R1 | 14B | INT4 Q8 FP16 | 38 tok/s 26 tok/s 13 tok/s | ~1.7s ~1.7s ~2.1s | |
- | AREX-2 | 27B | INT4 Q8 | 29 tok/s 16 tok/s | ~3.3s ~3.6s | |
- | PPLX Decider v1 27B | 27B | INT4 Q8 | 29 tok/s 16 tok/s | ~3.3s ~3.6s | |
- | PPLX Decider v1.1 27B | 27B | INT4 Q8 | 29 tok/s 16 tok/s | ~3.3s ~3.6s | |
- | Agnes 3.0 Flash | 33B | INT4 | 24 tok/s | ~4.0s | |
- | Falcon-40B | 40B | INT4 | 21 tok/s | ~4.8s | |
Inference Capacity
Maximum model parameter class runnable by weight precision.
Context:
4-bit
32B Models
8-bit
14B Models
16-bit
14B Models
Fine-Tuning Capacity
Hardware capacity for local training and adapter fine-tuning.
Context Length:
QLoRA
32B Models
LoRA
14B Models
Full Parameter Training
3B Models
Workload Recommendations
Guidance for optimal precision and operational ceilings on Radeon PRO W7800 (32GB).
Inference Sweet Spot
Optimized for 14B models at uncompressed or Q8 precision, and 32B models at Q4 with up to 32k context.
Bandwidth & Speed Profile
With 576 GB/s aggregate bandwidth, batch size 1 inference operates in a memory-bandwidth bound regime. Generates approximately 128 tok/s on an 8B Q4 model and 15 tok/s on a 70B Q4 model.
Frequently Asked Questions
©2025 ApX Machine Learning