Yes, just — 2.4 GB spare
Gemma 4 26B-A4B at Q4_K_M fits your RTX 4000 Ada entirely on the GPU at 8K context, at an estimated 39 tokens per second. Past 69K the KV cache pushes it over — quantise the cache to q8_0, or step down a quantisation, to go longer.
Mixture of experts with 3.8B active. Slower to think than Qwen3.6 35B-A3B, faster to answer, and it sees images.
Hardware requirements What hardware do I need to run Gemma 4 26B-A4B? →At Q4_K_M with an 8K context: a 24 GB GPU (RTX 4090) or a 32 GB Mac (M4). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.
The VRAM budget
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| Q8_0 | 26.2 GB | 27.3 GB | — | ~8.2 | −0.1% ppl | 8.9 GB over |
| Q6_K | 20.2 GB | 21.3 GB | — | ~17 | −0.4% ppl | 2.9 GB over |
| Q5_K_M | 17.5 GB | 18.6 GB | 2K | ~32 | −0.8% ppl | 0.2 GB over |
| Q4_K_M | 14.9 GB | 16.0 GB | 69K | 39 | −1.9% ppl | Recommended |
| Q3_K_M | 12.1 GB | 13.2 GB | 141K | 48 | −5.4% ppl | Long context |
| Q2_K | 10.3 GB | 11.4 GB | 186K | 57 | −15% ppl | Long context |
Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it. This model interleaves sliding-window layers (1024 tokens, 5 of 30 layers global), which is why its cache barely grows with context.
How to run it
$ llama-server \
-hf google/gemma-4-26B-A4B-it:Q4_K_M \
-c 8192 -ngl 99
The engine underneath most of the others. Every knob is exposed. More on llama.cpp.
Related models on an RTX 4000 Ada
| Model | Total | Tok/s est. | |
|---|---|---|---|
| Gemma 4 31B 31.3B · same family |
Q4_K_M · 20.2 GB | ~8.1 | CPU offload |
| Gemma 4 12B 12B · same family |
Q4_K_M · 8.2 GB | 32 | Runs great |
| Gemma 4 E4B 8.0B · same family |
Q4_K_M · 5.2 GB | 48 | Runs great |
| Gemma 4 E2B 5.1B · same family |
Q4_K_M · 3.5 GB | 76 | Runs great |
| Gemma 3 27B 27.4B · similar size |
Q4_K_M · 17.0 GB | 14 | Tight fit |
| Qwen3.8 27B 27.8B · similar size |
Q4_K_M · 16.7 GB | 14 | Tight fit |
| Qwen3.6 27B 27.8B · similar size |
Q4_K_M · 16.7 GB | 14 | Tight fit |
Gemma 4 26B-A4B on other hardware
| Device | Total | Tok/s est. | |
|---|---|---|---|
| GeForce RTX 4060 Laptop 7.0 GB usable · 256 GB/s |
16.0 GB | ~9.4 | CPU offload |
| GeForce RTX 3060 12 GB 10.6 GB usable · 360 GB/s |
16.0 GB | ~14 | CPU offload |
| M4 · 16 GB 10.7 GB usable · 120 GB/s |
16.0 GB | — | Won't fit |
| GeForce RTX 4090 22.4 GB usable · 1008 GB/s |
16.0 GB | 110 | Runs great |
| Radeon RX 7900 XTX 22.4 GB usable · 960 GB/s |
16.0 GB | 105 | Runs great |
| M4 · 32 GB 24.0 GB usable · 120 GB/s |
16.0 GB | 15 | Runs great |
| M3 Max · 64 GB 48.0 GB usable · 400 GB/s |
16.0 GB | 49 | Runs great |