All hardware / RX 7900 XTX
With 24 GB of VRAM, the RX 7900 XTX runs 14 of 22 popular open models fully in fast memory at Q4_K_M or better (8K context, assuming 32 GB of DDR5 system RAM). The largest that fit are Qwen3.6 35B-A3B (Q4_K_M), Gemma 4 31B (Q5_K_M), Granite 4.2 30B (Q5_K_M). Fastest: Qwen3.6 35B-A3B at over 150 tokens/sec and Gemma 4 E2B at over 150 tokens/sec. 1 more runs with offload to system RAM, but slower.
Check with your own RAM and context length| Model | Result | Best quant | Memory needed | Est. speed |
|---|---|---|---|---|
| Qwen3.6 35B-A3B | Runs on GPU | Q4_K_M | 22.2 GB | 150+ tok/s |
| Gemma 4 E2B | Runs on GPU | Q8_0 | 6.1 GB | 150+ tok/s |
| Gemma 4 26B A4B | Runs on GPU | Q6_K | 21.8 GB | 150+ tok/s |
| gpt-oss-20b | Runs on GPU | Q8_0 | 23.2 GB | 150+ tok/s |
| Ministral 3 3B | Runs on GPU | Q8_0 | 4.8 GB | 143 tok/s |
| Gemma 4 E4B | Runs on GPU | Q8_0 | 9.3 GB | 120 tok/s |
| Qwen3.5 9B | Runs on GPU | Q8_0 | 11.3 GB | 56 tok/s |
| Gemma 4 12B | Runs on GPU | Q8_0 | 13.8 GB | 45 tok/s |
| Phi-4 14B | Runs on GPU | Q8_0 | 17.7 GB | 37 tok/s |
| Mistral Small 3.1 24B | Runs on GPU | Q6_K | 21.5 GB | 29 tok/s |
| Qwen3.8 27B | Runs on GPU | Q5_K_M | 20.9 GB | 29 tok/s |
| Granite 4.2 30B | Runs on GPU | Q5_K_M | 21.6 GB | 28 tok/s |
| Gemma 4 31B | Runs on GPU | Q5_K_M | 23.0 GB | 26 tok/s |
| Qwen3.6 27B | Runs on GPU | Q6_K | 23.2 GB | 26 tok/s |
| Hermes 4.3 36B | Lower quality fit | Q3_K_M | 19.7 GB | 33 tok/s |
| Llama 3.3 70B | Needs offload | Q4_K_M | 45.9 GB | 1.9 tok/s |
| Llama 4 Scout | Too big | Q4_K_M | 68.1 GB | — |
| gpt-oss-120b | Too big | Q4_K_M | 72.0 GB | — |
| Qwen3.5 122B-A10B | Too big | Q4_K_M | 75.3 GB | — |
| Qwen3.8-Flash-Next | Too big | Q4_K_M | 107.8 GB | — |
| GLM-5.3-Flash | Too big | Q4_K_M | 196.0 GB | — |
| DeepSeek V4.1-Flash | Too big | Q4_K_M | 335.8 GB | — |
OllamaLM StudioJanGPT4AllAnythingLLMllama.cppvLLMSGLangKoboldCppText Generation WebUILocalAI