GPU ARuns more models
AMD RX 7900 XTX
- VRAM
- 24 GB
- Bandwidth
- 960 GB/s
- Street price
- $879
- Vendor
- amd
GPU B
NVIDIA RTX 4060
- VRAM
- 8 GB
- Bandwidth
- 272 GB/s
- Street price
- $479
- Vendor
- nvidia
The short answer
AMD RX 7900 XTX can run 15 models that NVIDIA RTX 4060 can't fit in VRAM — mostly the larger models. For the 18 models both can handle, speeds are similar. If you want headroom for bigger models, AMD RX 7900 XTX is the clear choice.
15 models A runs, B can't
16 models A is 20%+ faster
2 equal (both run, <20% diff)
21 too large for either
Model-by-model fit
Click any row for the full breakdown. Tie% shown in the Winner column when both GPUs run the model within 20% of each other.
| Model | AMD RX 7900 XTX | NVIDIA RTX 4060 | Winner |
|---|---|---|---|
c4ai-command-r-v01 35B 35B · command | 40 tok/s · Q4_K_M | Too large | A (only) |
Command-R+ 104B 104B · command | Too large | Too large | — |
DeepSeek R1 Distill Llama 8B 8B · deepseek | 49 tok/s · FP16 | 33 tok/s · Q6_K | A (faster) |
DeepSeek R1 Distill Qwen 14B 14.8B · deepseek | 53 tok/s · Q8_0 | Too large | A (only) |
DeepSeek R1 Distill Llama 70B 70.6B · deepseek | Too large | Too large | — |
DeepSeek R1 671B 671B · deepseek | Too large | Too large | — |
DeepSeek-V3 685B 685B · deepseek | Too large | Too large | — |
DeepSeek-V3.2 685.4B 685.4B · deepseek | Too large | Too large | — |
gemma-2-9b 9.2B · gemma | 43 tok/s · FP16 | 41 tok/s · Q4_K_M | ≈tie A +5% |
gemma-2-27b 27.2B · gemma | 36 tok/s · Q6_K | Too large | A (only) |
Llama 3.1 8B Compact 8B · llama | 44 tok/s · FP16 | 31 tok/s · Q6_K | A (faster) |
CodeLlama 34B 34B · llama | 42 tok/s · Q4_K_M | Too large | A (only) |
CodeLlama 34B 34B · llama | 42 tok/s · Q4_K_M | Too large | A (only) |
Llama 3.3 70B 70.6B · llama | Too large | Too large | — |
Llama 3.1 70B 70.6B · llama | Too large | Too large | — |
Llama 4 Scout 17B 109B · llama | Too large | Too large | — |
Llama-4-Maverick-17B-128E 400B · llama | Too large | Too large | — |
Llama 3.1 405B 405B · llama | Too large | Too large | — |
Mistral 7B v0.1 7.25B · mistral | 54 tok/s · FP16 | 36 tok/s · Q6_K | A (faster) |
Codestral 22B 22.2B · mistral | 43 tok/s · Q6_K | Too large | A (only) |
Mixtral 8x7B Instruct v0.1 47B · mixtral | Too large | Too large | — |
Mistral Large 2 123B 123B · mistral | Too large | Too large | — |
Phi-4-mini 3.8B 3.8B · phi | 101 tok/s · FP16 | 54 tok/s · Q8_0 | A (faster) |
Phi-4 14B 14B · phi | 51 tok/s · Q8_0 | Too large | A (only) |
Qwen 2.5 1.5B 1.5B · qwen | 234 tok/s · FP16 | 66 tok/s · FP16 | A (faster) |
Qwen 2.5 3B 3.1B · qwen | 122 tok/s · FP16 | 35 tok/s · FP16 | A (faster) |
Qwen3.5-4B 4.7B · qwen | 83 tok/s · FP16 | 45 tok/s · Q8_0 | A (faster) |
Qwen 2.5 7B 7.6B · qwen | 52 tok/s · FP16 | 35 tok/s · Q6_K | A (faster) |
Qwen 2.5 7B 7.6B · qwen | 52 tok/s · FP16 | 35 tok/s · Q6_K | A (faster) |
Qwen 3 8B 8B · qwen | 44 tok/s · FP16 | 31 tok/s · Q6_K | A (faster) |
Qwen3.5-9B 9.7B · qwen | 41 tok/s · FP16 | 39 tok/s · Q4_K_M | ≈tie A +5% |
Qwen 3 32B 32B · qwen | 39 tok/s · Q4_K_M | Too large | A (only) |
Qwen3.5-35B-A3B 36B · qwen | 39 tok/s · Q4_K_M | Too large | A (only) |
Qwen 2.5 72B 72.7B · qwen | Too large | Too large | — |
Qwen 2.5 72B 72.7B · qwen | Too large | Too large | — |
Llama 3.2 1B 1.24B · llama | 286 tok/s · FP16 | 81 tok/s · FP16 | A (faster) |
Llama 4 Scout 17B 109B · llama | Too large | Too large | — |
DeepSeek R1 671B 671B · deepseek | Too large | Too large | — |
Gemma 3 27B 27B · gemma | 38 tok/s · Q5_K_M | Too large | A (only) |
Qwen 3 8B 8B · qwen | 44 tok/s · FP16 | 31 tok/s · Q6_K | A (faster) |
Qwen 3 32B 32B · qwen | 39 tok/s · Q4_K_M | Too large | A (only) |
Llama 3.1 8B Compact 8B · llama | 44 tok/s · FP16 | 31 tok/s · Q6_K | A (faster) |
Mixtral 8x7B Instruct v0.1 47B · mixtral | Too large | Too large | — |
Mistral Small 3.2 24B 24B · mistral | 43 tok/s · Q6_K | Too large | A (only) |
Command A 111B 111B · command | Too large | Too large | — |
DeepSeek R1 0528 685B · deepseek | Too large | Too large | — |
DeepSeek-V3-0324 684.5B · deepseek | Too large | Too large | — |
DeepSeek-R1-0528-Qwen3-8B 8.2B · qwen | 51 tok/s · FP16 | 36 tok/s · Q6_K | A (faster) |
Qwen3-235B-A22B-Instruct-2507 235B · qwen | Too large | Too large | — |
Qwen3-30B-A3B-Instruct-2507 30B · qwen | 50 tok/s · Q4_K_M | Too large | A (only) |
Qwen3-4B-Instruct-2507 4B · qwen | 104 tok/s · FP16 | 59 tok/s · Q8_0 | A (faster) |
gemma-4-E4B-it 8B · gemma | 52 tok/s · FP16 | 36 tok/s · Q6_K | A (faster) |
gemma-4-26B-A4B-it 26.5B · gemma | 39 tok/s · Q6_K | Too large | A (only) |
gemma-4-31B-it 32.7B · gemma | 45 tok/s · Q4_K_M | Too large | A (only) |
Want a different pairing? Browse all comparisons →