Gemma 4 26B A4B IT vs Gemma 4 31B IT
Gemma 4 26B A4B IT and Gemma 4 31B IT match in llmrun Score, with values of 105.4 versus 106.1; both fit 24 GB at Q4_K_M; Gemma 4 26B A4B IT is 5.3× faster on RTX 4090 (~171 vs ~32 tok/s).
Model A · Google
Gemma 4 26B A4B IT25.8B · 4.4B active · 256K context · Apache 2.0 · Mar 2026
Model B · Google
Gemma 4 31B IT31.3B · 256K context · Apache 2.0 · Mar 2026
Choose Gemma 4 26B A4B IT if you want…
Fits a 12 GB GPU
IQ3_S · 12 GB; Gemma 4 31B IT needs 11.5 GB at its smallest quant
5.3× faster on RTX 4090
~171 vs ~32 tok/s
Lighter on memory
16.1 vs 20.4 GB at Q4_K_M
Choose Gemma 4 31B IT if you want…
Stronger at reasoning
109.3 vs 100.8
Ahead on the benchmarks
8 of 10 shared boards
On your hardware
Each model at its default quant (Q4_K_M), a smaller one when it must. Estimates, ±20%.
8 GB
RTX 4060 · 8 GB tier
Gemma 4 26B A4B IT
Doesn't fit
smallest quant needs 8.1 GB
Gemma 4 31B IT
Doesn't fit
smallest quant needs 11.5 GB
12 GB
RTX 3060 12GB · 12 GB tier
Gemma 4 26B A4B IT
IQ3_S · ~99 tok/s
12 GB · up to 16Kbetter quant
Gemma 4 31B IT
IQ2_XXS · ~23 tok/s
11.5 GB · up to 16K
16 GB
RTX 5060 Ti 16GB · 16 GB tier
Gemma 4 26B A4B IT
Q4_1 · ~95 tok/s
15.5 GB · up to 16Kbetter quant
Gemma 4 31B IT
IQ3_XS · ~20 tok/s
15.8 GB · up to 16K
24 GBreference
RTX 4090 · 24 GB tier
Gemma 4 26B A4B IT
Q4_K_M · ~171 tok/s
16.5 GB · up to 128Kfaster
Gemma 4 31B IT
Q4_K_M · ~32 tok/s
21.7 GB · up to 32K
32 GB
RTX 5090 · 32 GB tier
Gemma 4 26B A4B IT
Q4_K_M · ~250 tok/s
16.5 GB · up to 256Kfaster
Gemma 4 31B IT
Q4_K_M · ~57 tok/s
21.7 GB · up to 64K
48 GB
RTX A6000 · 48 GB tier
Gemma 4 26B A4B IT
Q4_K_M · ~140 tok/s
16.5 GB · up to 256Kfaster
Gemma 4 31B IT
Q4_K_M · ~25 tok/s
21.7 GB · up to 128K
Mac 32 GB
Mac Mini M4 · Macs
Gemma 4 26B A4B IT
Q4_K_M · ~26 tok/s
16.5 GB · up to 256Kfaster
Gemma 4 31B IT
Q4_K_M · ~4 tok/s
21.7 GB · up to 64K
Mac 64 GB
Mac Studio M4 Max · Macs
Gemma 4 26B A4B IT
Q4_K_M · ~76 tok/s
16.5 GB · up to 256Kfaster
Gemma 4 31B IT
Q4_K_M · ~19 tok/s
21.7 GB · up to 256K
Mac 128 GB
Mac Studio M4 Max · Macs
Gemma 4 26B A4B IT
Q4_K_M · ~76 tok/s
16.5 GB · up to 256Kfaster
Gemma 4 31B IT
Q4_K_M · ~19 tok/s
21.7 GB · up to 256K
Reference GPU: RTX 4090. Tinted cell = the better pick on that machine (fits, more headroom, or at least 10% faster).
Overall
Gemma 4 26B A4B IT
Gemma 4 31B IT
Coding
Gemma 4 26B A4B IT
Gemma 4 31B IT
Science
Gemma 4 26B A4B IT
Gemma 4 31B IT
Reasoning
Gemma 4 26B A4B IT
Gemma 4 31B IT
Gemma 4 26B A4B IT · #37 of 92 open models · #6 of 34 that fit 24 GB
Gemma 4 31B IT · #35 of 92 open models · #4 of 34 that fit 24 GB
Benchmarks
10 shared boards: Gemma 4 26B A4B IT leads 2, Gemma 4 31B IT leads 8 · Benchmarks imported Oct 2026
Gemma 4 26B A4B IT
73.2%#29/97 open
IndependentEpoch AI · Apr 2026
Gemma 4 31B IT
75.8%#27/97 open
IndependentEpoch AI · Apr 2026
Gemma 4 26B A4B IT
1437.6#23/186 open
ArenaLMArena · Oct 2026
Gemma 4 31B IT
1452.4#14/186 open
ArenaLMArena · Oct 2026
Gemma 4 26B A4B IT
82.2%#23/85 open
IndependentEpoch AI · Apr 2026
Gemma 4 31B IT
73.3%#25/85 open
IndependentEpoch AI · Apr 2026
Gemma 4 26B A4B IT
1359.0#33/50 open
ArenaLMArena · Oct 2026
Gemma 4 31B IT
1365.9#30/50 open
ArenaLMArena · Oct 2026
Gemma 4 26B A4B IT
40.1%#30/65 open
Lab-reportedEpoch AI · Apr 2026
Gemma 4 31B IT
43.4%#23/65 open
Lab-reportedEpoch AI · Apr 2026
Gemma 4 26B A4B IT
35.2%#34/46 open
IndependentEpoch AI · Apr 2026
Gemma 4 31B IT
52.3%#9/46 open
IndependentEpoch AI · Apr 2026
Gemma 4 26B A4B IT
6.0%#27/67 open
IndependentEpoch AI · Apr 2026
Gemma 4 31B IT
5.0%#29/67 open
IndependentEpoch AI · Apr 2026
Gemma 4 26B A4B IT
0.0%#50/65 open
Lab-reportedEpoch AI · Apr 2026
Gemma 4 31B IT
1.4%#29/65 open
Lab-reportedEpoch AI · Apr 2026
Gemma 4 26B A4B IT
74.9%#29/68 open
Lab-reportedEpoch AI · Apr 2026
Gemma 4 31B IT
82.7%#19/68 open
Lab-reportedEpoch AI · Apr 2026
Gemma 4 26B A4B IT
29.7%#20/54 open
Lab-reportedEpoch AI · Apr 2026
Gemma 4 31B IT
39.3%#9/54 open
Lab-reportedEpoch AI · Apr 2026
3 more boards (other shared and single-model boards)
Gemma 4 26B A4B IT
927.2#11/42 open
Lab-reportedEpoch AI · Apr 2026
Gemma 4 31B IT
925.5#12/42 open
Lab-reportedEpoch AI · Apr 2026
Only Gemma 4 31B IT (2)
- SimpleQA10.4%
- Surface Evolver Bench30.6%
VRAM by quantization
Memory to load the model and 2K context; below it, the total at 32K and 128K context. Lighter side in bold.
Q2_K
Gemma 4 26B A4B IT
11.6 GB11.0 GB file
32K 12.5 GB · 128K 15.8 GB
Gemma 4 31B IT
14.9 GB12.6 GB file
32K 18.4 GB · 128K 31.0 GB
Q3_K_S
Gemma 4 26B A4B IT
11.9 GB12.6 GB file
32K 12.8 GB · 128K 16.2 GB
Gemma 4 31B IT
15.3 GB13.2 GB file
32K 18.7 GB · 128K 31.4 GB
Q3_K_M
Gemma 4 26B A4B IT
13.2 GB12.7 GB file
32K 14.1 GB · 128K 17.5 GB
Gemma 4 31B IT
16.9 GB14.7 GB file
32K 20.3 GB · 128K 33.0 GB
Q4_0
Gemma 4 26B A4B IT
13.6 GB~12.9 GB file
32K 14.5 GB · 128K 17.8 GB
Gemma 4 31B IT
17.3 GB17.3 GB file
32K 20.7 GB · 128K 33.4 GB
Q4_K_M
Gemma 4 26B A4B IT
16.1 GB16.9 GB file
32K 17.0 GB · 128K 20.4 GB
Gemma 4 31B IT
20.4 GB18.3 GB file
32K 23.8 GB · 128K 36.5 GB
Q5_K_M
Gemma 4 26B A4B IT
19.0 GB21.2 GB file
32K 19.9 GB · 128K 23.3 GB
Gemma 4 31B IT
23.9 GB21.7 GB file
32K 27.3 GB · 128K 40.0 GB
Q6_K
Gemma 4 26B A4B IT
21.9 GB23.2 GB file
32K 22.8 GB · 128K 26.2 GB
Gemma 4 31B IT
27.4 GB25.2 GB file
32K 30.9 GB · 128K 43.5 GB
Q8_0
Gemma 4 26B A4B IT
26.5 GB~25.8 GB file
32K 27.4 GB · 128K 30.7 GB
Gemma 4 31B IT
32.9 GB~31.3 GB file
32K 36.3 GB · 128K 49.0 GB
19 more quants
IQ2_XXS
Gemma 4 26B A4B IT
7.7 GB9.9 GB file
32K 8.6 GB · 128K 12.0 GB
Gemma 4 31B IT
10.2 GB8.5 GB file
32K 13.7 GB · 128K 26.3 GB
IQ2_XS
Gemma 4 26B A4B IT
8.4 GB10.1 GB file
32K 9.3 GB · 128K 12.6 GB
Gemma 4 31B IT
11.0 GB11.5 GB file
32K 14.4 GB · 128K 27.1 GB
IQ2_S
Gemma 4 26B A4B IT
8.7 GB10.2 GB file
32K 9.6 GB · 128K 12.9 GB
Gemma 4 31B IT
11.4 GB12.1 GB file
32K 14.8 GB · 128K 27.5 GB
IQ2_M
Gemma 4 26B A4B IT
9.4 GB10.0 GB file
32K 10.3 GB · 128K 13.6 GB
Gemma 4 31B IT
12.2 GB10.8 GB file
32K 15.6 GB · 128K 28.3 GB
IQ3_XXS
Gemma 4 26B A4B IT
10.7 GB11.4 GB file
32K 11.6 GB · 128K 14.9 GB
Gemma 4 31B IT
13.7 GB11.8 GB file
32K 17.2 GB · 128K 29.9 GB
Q2_K_S
Gemma 4 26B A4B IT
11.0 GB10.6 GB file
32K 11.9 GB · 128K 15.2 GB
Gemma 4 31B IT
14.1 GB11.0 GB file
32K 17.6 GB · 128K 30.3 GB
IQ3_XS
Gemma 4 26B A4B IT
11.3 GB12.4 GB file
32K 12.2 GB · 128K 15.5 GB
Gemma 4 31B IT
14.5 GB13.8 GB file
32K 18.0 GB · 128K 30.6 GB
IQ3_S
Gemma 4 26B A4B IT
11.6 GB11.3 GB file
32K 12.5 GB · 128K 15.8 GB
Gemma 4 31B IT
14.9 GB13.8 GB file
32K 18.4 GB · 128K 31.0 GB
IQ3_M
Gemma 4 26B A4B IT
12.3 GB13.3 GB file
32K 13.2 GB · 128K 16.5 GB
Gemma 4 31B IT
15.7 GB15.1 GB file
32K 19.1 GB · 128K 31.8 GB
Q3_K_L
Gemma 4 26B A4B IT
13.9 GB13.2 GB file
32K 14.8 GB · 128K 18.1 GB
Gemma 4 31B IT
17.7 GB16.8 GB file
32K 21.1 GB · 128K 33.8 GB
IQ4_XS
Gemma 4 26B A4B IT
14.5 GB13.6 GB file
32K 15.4 GB · 128K 18.7 GB
Gemma 4 31B IT
18.4 GB16.4 GB file
32K 21.9 GB · 128K 34.6 GB
IQ4_NL
Gemma 4 26B A4B IT
15.2 GB13.6 GB file
32K 16.1 GB · 128K 19.4 GB
Gemma 4 31B IT
19.2 GB17.3 GB file
32K 22.7 GB · 128K 35.3 GB
Q4_1
Gemma 4 26B A4B IT
15.2 GB16.1 GB file
32K 16.1 GB · 128K 19.4 GB
Gemma 4 31B IT
19.2 GB19.1 GB file
32K 22.7 GB · 128K 35.3 GB
Q4_K_S
Gemma 4 26B A4B IT
15.2 GB16.5 GB file
32K 16.1 GB · 128K 19.4 GB
Gemma 4 31B IT
19.2 GB17.4 GB file
32K 22.7 GB · 128K 35.3 GB
Q4_K_L
Gemma 4 26B A4B IT
16.5 GB17.2 GB file
32K 17.4 GB · 128K 20.7 GB
Gemma 4 31B IT
20.8 GB19.9 GB file
32K 24.2 GB · 128K 36.9 GB
Q5_0
Gemma 4 26B A4B IT
16.8 GB17.5 GB file
32K 17.7 GB · 128K 21.0 GB
Gemma 4 31B IT
21.2 GB21.3 GB file
32K 24.6 GB · 128K 37.3 GB
Q5_K_S
Gemma 4 26B A4B IT
18.4 GB18.9 GB file
32K 19.3 GB · 128K 22.6 GB
Gemma 4 31B IT
23.1 GB21.1 GB file
32K 26.6 GB · 128K 39.2 GB
Q5_K_L
Gemma 4 26B A4B IT
19.4 GB19.5 GB file
32K 20.3 GB · 128K 23.6 GB
Gemma 4 31B IT
24.3 GB23.0 GB file
32K 27.7 GB · 128K 40.4 GB
BF16
Gemma 4 26B A4B IT
52.3 GB~51.6 GB file
32K 53.2 GB · 128K 56.5 GB
Gemma 4 31B IT
64.2 GB~62.5 GB file
32K 67.6 GB · 128K 80.3 GB
Gemma 4 26B A4B IT
Ollama · Q4_K_M
ollama run hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:Q4_K_MGemma 4 31B IT
Ollama · Q4_K_M
ollama run hf.co/unsloth/gemma-4-31B-it-GGUF:Q4_K_M| Spec | Gemma 4 26B A4B IT | Gemma 4 31B IT |
|---|---|---|
| Publisher | ||
| Parameters | 25.8B | 31.3B |
| Active parameters | 4.4B per token | — |
| Architecture | Gemma4ForConditionalGeneration | Gemma4ForConditionalGeneration |
| Context | 256K tokens | 256K tokens |
| Modalities | Vision, Function-calling | Vision, Function-calling |
| License | Apache 2.0 | Apache 2.0 |
| Released | Mar 2026 | Mar 2026 |
Frequently Asked Questions
Which is better, Gemma 4 26B A4B IT or Gemma 4 31B IT?
Gemma 4 26B A4B IT and Gemma 4 31B IT match in llmrun Score, with values of 105.4 versus 106.1; both fit 24 GB at Q4_K_M; Gemma 4 26B A4B IT is 5.3× faster on RTX 4090 (~171 vs ~32 tok/s). Choose Gemma 4 26B A4B IT for fits a 12 GB GPU and 5.3× faster on RTX 4090; choose Gemma 4 31B IT for stronger at reasoning and ahead on the benchmarks.
Which needs less VRAM, Gemma 4 26B A4B IT or Gemma 4 31B IT?
At Q4_K_M, Gemma 4 26B A4B IT requires 16.1 GB while Gemma 4 31B IT needs 20.4 GB, making Gemma 4 26B A4B IT the easier model to run on your local setup.
Which is faster on RTX 4090?
Estimated decode speed on RTX 4090 is about 171 tok/s for Gemma 4 26B A4B IT (Q4_K_M) and 32 tok/s for Gemma 4 31B IT (Q4_K_M), so Gemma 4 26B A4B IT is faster. Estimates, ±20%.
Can I run Gemma 4 26B A4B IT or Gemma 4 31B IT on a 16 GB GPU?
Gemma 4 26B A4B IT fits at Q4_1; Gemma 4 31B IT fits at IQ3_XS.
Which has a longer context window, Gemma 4 26B A4B IT or Gemma 4 31B IT?
Gemma 4 26B A4B IT supports 262,144 tokens and Gemma 4 31B IT supports 262,144 tokens.