Can Gemma 4 26B A4B IT run on the A100 40GB?
Yes. At 8K context the best fit is Q8_0, using about 26.4 GB of the 38.0 GB usable on the A100 40GB. Estimated speed ceiling: ~373 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) | 10.3 GB Fits | 10.4 GB Fits | 11.4 GB Fits | 15.1 GB Fits | 1037 |
| 3-bit (Q3_K_M) • | 13.1 GB Fits | 13.3 GB Fits | 14.2 GB Fits | 17.9 GB Fits | 788 |
| 4-bit (Q4_K_M) • | 17.0 GB Fits | 17.2 GB Fits | 18.1 GB Fits | 21.9 GB Fits | 592 |
| 5-bit (Q5_K_M) • | 20.9 GB Fits | 21.1 GB Fits | 22.0 GB Fits | 25.8 GB Fits | 474 |
| 6-bit (Q6_K) • | 22.8 GB Fits | 23.0 GB Fits | 23.9 GB Fits | 27.7 GB Fits | 433 |
| 8-bit (Q8_0) • | 26.3 GB Fits | 26.4 GB Fits | 27.4 GB Fits | 31.1 GB Fits | 373 |
| 16-bit (F16/BF16) • | 48.3 GB No | 48.4 GB No | 49.4 GB No | 53.1 GB No | — |
• real GGUF file size from unsloth/gemma-4-26B-A4B-it-GGUF. Speed is a bandwidth ceiling (1555 GB/s), not a benchmark. Methodology.
What fits instead
- Cheapest listed GPU that runs Gemma 4 26B A4B IT: RX 7900 XTX (24 GB, launch MSRP $999) at Q4_K_M, fully in VRAM at 8K context.
- Largest popular model that fits the A100 40GB: Qwen3.6 35B A3B (36B, MoE) at Q6_K, about 29.0 GB at 8K context.
"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.
More
Gemma 4 26B A4B IT on every GPU and Mac · Every model that runs on the A100 40GB · Other models that fit 48 GB VRAM · Try other settings in the calculator
Guides: Best GPU for local LLMs by budget · Can I run gpt-oss, Llama 70B or Qwen3? · Mac vs PC for local LLMs
Data: Hugging Face Hub (google/gemma-4-26B-A4B-it), NVIDIA specs. Model data last checked 2026-11-17; refreshed hourly.