Can the RTX 6000D run Gemma 4 26B A4B?
Yes. Gemma 4 26B A4B fits the RTX 6000D's 84 GB at Q4_K_M (about 16.8 GB needed), running at an estimated 265 tok/s. There's room for up to FP16 if you want higher quality.
Every quantization
Gemma 4 26B A4B (26.5B, 4B active) on 84 GB
| Quant | Weights | Needs | Fit | Est. speed |
|---|---|---|---|---|
| Q4_K_M | 15 GB | 16.8 GB | Fits easily | ~265 tok/s |
| Q5_K_M | 19 GB | 20.8 GB | Fits easily | ~209 tok/s |
| Q8_0 | 28 GB | 29.8 GB | Fits easily | ~142 tok/s |
| FP16 | 53 GB | 54.8 GB | Fits | ~75 tok/s |
Estimates. Needs = weights + 1.8 GB for KV cache and runtime at modest context. Speed is single-stream decode scaled from the RTX 6000D's 1570 GB/s bandwidth (Estimated from memory bandwidth (llama.cpp decode)). Long contexts need more memory and run slower.
Run it
Copy, paste, go
llama-server -hf google/gemma-4-26B-A4B-it-qat-q4_0-gguf -ngl 99Ollama pulls a Q4 build by default. Pick a larger quant only if the table above says it fits. Full Gemma 4 26B A4B details →
Compare
Same model, other hardware - and other models on this card
Gemma 4 26B A4B on other hardware
- RTX 5090~303 tok/s
- RTX 5090 D~302 tok/s
- RTX 4090~184 tok/s
- Radeon RX 7900 XTX~162 tok/s
- RTX 3090~161 tok/s
- MacBook Pro 16" M4 Max~92 tok/s
- Arc Pro B60~77 tok/s
- DGX Spark (GB10)~46 tok/s
Also runs on the RTX 6000D
- Qwen2.5 72B~23 tok/s
- Llama 3.3 70B~23 tok/s
- Qwen3.6 35B A3B~343 tok/s
- Qwen3.5 35B A3B~343 tok/s
- dolphin-2.9.1-yi-1.5-34b~45 tok/s
- Gemma 4 31B~47 tok/s
- Qwen3 32B~47 tok/s
- GLM-4.7-Flash~347 tok/s
Frequently asked
Quick answers
Can the RTX 6000D run Gemma 4 26B A4B?
Yes. Gemma 4 26B A4B fits the RTX 6000D's 84 GB at Q4_K_M (about 16.8 GB needed), running at an estimated 265 tok/s. There's room for up to FP16 if you want higher quality.
How much VRAM does Gemma 4 26B A4B need?
About 15 GB of weights at Q4_K_M, 28 GB at Q8_0 and 53 GB at FP16. Add roughly 1.8 GB for the KV cache and runtime at modest context lengths.
How fast is Gemma 4 26B A4B on the RTX 6000D?
Roughly 265 tokens per second at Q4_K_M (single user, llama.cpp-style decode). This is an estimate from the RTX 6000D's 1570 GB/s memory bandwidth; as a mixture-of-experts model only about 4B parameters are read per token, which is why it is faster than its size suggests.