Gemma 2 9B IT vs Gemma 4 26B A4B IT
Gemma 4 26B A4B IT leads llmrun Score 105.8 to 68.0; both fit 24 GB at Q4_K_M; Gemma 4 26B A4B IT is 1.6× faster on RTX 4090 (~171 vs ~107 tok/s).
Model B · Google
Gemma 4 26B A4B IT25.8B · 4.4B active · 256K context · Apache 2.0 · Mar 2026
Choose Gemma 2 9B IT if you want…
Fits an 8 GB GPU
Q4_K_M · 7.3 GB; Gemma 4 26B A4B IT needs 8.1 GB at its smallest quant
Lighter on memory
6.1 vs 16.1 GB at Q4_K_M
Also does chat
Gemma 4 26B A4B IT doesn't list it
Choose Gemma 4 26B A4B IT if you want…
Higher llmrun Score
105.8 vs 68.0
1.6× faster on RTX 4090
~171 vs ~107 tok/s
Longer context window
256K vs 8K tokens
Also does vision, function-calling
Gemma 2 9B IT doesn't list it
More permissive license
Apache 2.0 vs Gemma Terms
Newer release
Mar 2026 vs Jun 2024
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 2 9B IT
Q4_K_M · ~29 tok/s
7.3 GB · up to 8Kfits
Gemma 4 26B A4B IT
Doesn't fit
smallest quant needs 8.1 GB
12 GB
RTX 3060 12GB · 12 GB tier
Gemma 2 9B IT
Q4_K_M · ~38 tok/s
7.3 GB · up to 8Kmore headroom
Gemma 4 26B A4B IT
IQ3_S · ~99 tok/s
12 GB · up to 16K
16 GB
RTX 5060 Ti 16GB · 16 GB tier
Gemma 2 9B IT
Q4_K_M · ~48 tok/s
7.3 GB · up to 8Kmore headroom
Gemma 4 26B A4B IT
Q4_1 · ~95 tok/s
15.5 GB · up to 16K
24 GBreference
RTX 4090 · 24 GB tier
Gemma 2 9B IT
Q4_K_M · ~107 tok/s
7.3 GB · up to 8K
Gemma 4 26B A4B IT
Q4_K_M · ~171 tok/s
16.5 GB · up to 128Kfaster
32 GB
RTX 5090 · 32 GB tier
Gemma 2 9B IT
Q4_K_M · ~191 tok/s
7.3 GB · up to 8K
Gemma 4 26B A4B IT
Q4_K_M · ~250 tok/s
16.5 GB · up to 256Kfaster
48 GB
RTX A6000 · 48 GB tier
Gemma 2 9B IT
Q4_K_M · ~82 tok/s
7.3 GB · up to 8K
Gemma 4 26B A4B IT
Q4_K_M · ~140 tok/s
16.5 GB · up to 256Kfaster
Mac 32 GB
Mac Mini M4 · Macs
Gemma 2 9B IT
Q4_K_M · ~14 tok/s
7.3 GB · up to 8K
Gemma 4 26B A4B IT
Q4_K_M · ~26 tok/s
16.5 GB · up to 256Kfaster
Mac 64 GB
Mac Studio M4 Max · Macs
Gemma 2 9B IT
Q4_K_M · ~63 tok/s
7.3 GB · up to 8K
Gemma 4 26B A4B IT
Q4_K_M · ~76 tok/s
16.5 GB · up to 256Kfaster
Mac 128 GB
Mac Studio M4 Max · Macs
Gemma 2 9B IT
Q4_K_M · ~63 tok/s
7.3 GB · up to 8K
Gemma 4 26B A4B IT
Q4_K_M · ~76 tok/s
16.5 GB · up to 256Kfaster
Reference GPU: RTX 4090. Tinted cell = the better pick on that machine (fits, more headroom, or at least 10% faster).
Overall
Gemma 2 9B IT
Gemma 4 26B A4B IT
Coding
Gemma 2 9B IT
no data
Gemma 4 26B A4B IT
Science
Gemma 2 9B IT
no data
Gemma 4 26B A4B IT
Reasoning
Gemma 2 9B IT
no data
Gemma 4 26B A4B IT
Gemma 2 9B IT · #99 of 106 open models · #30 of 36 that fit 24 GB
Gemma 4 26B A4B IT · #45 of 106 open models · #5 of 36 that fit 24 GB
Benchmarks
2 shared boards: Gemma 2 9B IT leads 0, Gemma 4 26B A4B IT leads 2 · Benchmarks imported Nov 2026
Gemma 2 9B IT
27.5%#88/100 open
IndependentEpoch AI · Jun 2024
Gemma 4 26B A4B IT
73.2%#32/100 open
IndependentEpoch AI · Apr 2026
Gemma 2 9B IT
0.6%#84/88 open
IndependentEpoch AI · Jun 2024
Gemma 4 26B A4B IT
82.2%#26/88 open
IndependentEpoch AI · Apr 2026
11 more boards (other shared and single-model boards)
Gemma 2 9B IT
1267.0#125/188 open
ArenaLMArena · Oct 2026
Gemma 4 26B A4B IT
1437.6#22/188 open
ArenaLMArena · Oct 2026
Only Gemma 2 9B IT (3)
- MMLU-Pro52.1%
- MATH Level 521.0%
- MMLU72.1%
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 2 9B IT
4.3 GB3.8 GB file
32K — · 128K —
Gemma 4 26B A4B IT
11.6 GB11.0 GB file
32K 12.5 GB · 128K 15.8 GB
Q3_K_S
Gemma 2 9B IT
4.5 GB4.3 GB file
32K — · 128K —
Gemma 4 26B A4B IT
11.9 GB12.6 GB file
32K 12.8 GB · 128K 16.2 GB
Q3_K_M
Gemma 2 9B IT
5.0 GB4.8 GB file
32K — · 128K —
Gemma 4 26B A4B IT
13.2 GB12.7 GB file
32K 14.1 GB · 128K 17.5 GB
Q4_0
Gemma 2 9B IT
5.1 GB5.4 GB file
32K — · 128K —
Gemma 4 26B A4B IT
13.6 GB14.5 GB file
32K 14.5 GB · 128K 17.8 GB
Q4_K_M
Gemma 2 9B IT
6.1 GB5.8 GB file
32K — · 128K —
Gemma 4 26B A4B IT
16.1 GB16.9 GB file
32K 17.0 GB · 128K 20.4 GB
Q5_K_M
Gemma 2 9B IT
7.2 GB6.6 GB file
32K — · 128K —
Gemma 4 26B A4B IT
19.0 GB21.2 GB file
32K 19.9 GB · 128K 23.3 GB
Q6_K
Gemma 2 9B IT
8.4 GB7.6 GB file
32K — · 128K —
Gemma 4 26B A4B IT
21.9 GB23.2 GB file
32K 22.8 GB · 128K 26.2 GB
Q8_0
Gemma 2 9B IT
10.2 GB9.8 GB file
32K — · 128K —
Gemma 4 26B A4B IT
26.5 GB26.9 GB file
32K 27.4 GB · 128K 30.7 GB
20 more quants
IQ2_XXS
Gemma 2 9B IT
2.8 GB2.8 GB file
32K — · 128K —
Gemma 4 26B A4B IT
7.7 GB9.9 GB file
32K 8.6 GB · 128K 12.0 GB
IQ2_XS
Gemma 2 9B IT
3.1 GB3.1 GB file
32K — · 128K —
Gemma 4 26B A4B IT
8.4 GB10.1 GB file
32K 9.3 GB · 128K 12.6 GB
IQ2_S
Gemma 2 9B IT
3.2 GB3.2 GB file
32K — · 128K —
Gemma 4 26B A4B IT
8.7 GB10.2 GB file
32K 9.6 GB · 128K 12.9 GB
IQ2_M
Gemma 2 9B IT
3.4 GB3.4 GB file
32K — · 128K —
Gemma 4 26B A4B IT
9.4 GB10.0 GB file
32K 10.3 GB · 128K 13.6 GB
IQ3_XXS
Gemma 2 9B IT
3.9 GB3.8 GB file
32K — · 128K —
Gemma 4 26B A4B IT
10.7 GB11.4 GB file
32K 11.6 GB · 128K 14.9 GB
Q2_K_S
Gemma 2 9B IT
not listed
Gemma 4 26B A4B IT
11.0 GB10.6 GB file
32K 11.9 GB · 128K 15.2 GB
IQ3_XS
Gemma 2 9B IT
4.2 GB4.1 GB file
32K — · 128K —
Gemma 4 26B A4B IT
11.3 GB12.4 GB file
32K 12.2 GB · 128K 15.5 GB
IQ3_S
Gemma 2 9B IT
4.3 GB4.3 GB file
32K — · 128K —
Gemma 4 26B A4B IT
11.6 GB11.3 GB file
32K 12.5 GB · 128K 15.8 GB
IQ3_M
Gemma 2 9B IT
4.6 GB4.5 GB file
32K — · 128K —
Gemma 4 26B A4B IT
12.3 GB13.3 GB file
32K 13.2 GB · 128K 16.5 GB
Q3_K_L
Gemma 2 9B IT
5.2 GB5.1 GB file
32K — · 128K —
Gemma 4 26B A4B IT
13.9 GB13.2 GB file
32K 14.8 GB · 128K 18.1 GB
IQ4_XS
Gemma 2 9B IT
5.5 GB5.2 GB file
32K — · 128K —
Gemma 4 26B A4B IT
14.5 GB13.6 GB file
32K 15.4 GB · 128K 18.7 GB
IQ4_NL
Gemma 2 9B IT
not listed
Gemma 4 26B A4B IT
15.2 GB13.6 GB file
32K 16.1 GB · 128K 19.4 GB
Q4_1
Gemma 2 9B IT
5.7 GB6.0 GB file
32K — · 128K —
Gemma 4 26B A4B IT
15.2 GB16.1 GB file
32K 16.1 GB · 128K 19.4 GB
Q4_K_S
Gemma 2 9B IT
5.7 GB5.5 GB file
32K — · 128K —
Gemma 4 26B A4B IT
15.2 GB16.5 GB file
32K 16.1 GB · 128K 19.4 GB
Q4_K_L
Gemma 2 9B IT
6.2 GB6.0 GB file
32K — · 128K —
Gemma 4 26B A4B IT
16.5 GB17.2 GB file
32K 17.4 GB · 128K 20.7 GB
Q5_0
Gemma 2 9B IT
6.4 GB6.5 GB file
32K — · 128K —
Gemma 4 26B A4B IT
16.8 GB17.5 GB file
32K 17.7 GB · 128K 21.0 GB
Q5_1
Gemma 2 9B IT
7.0 GB7.0 GB file
32K — · 128K —
Gemma 4 26B A4B IT
not listed
Q5_K_S
Gemma 2 9B IT
7.0 GB6.5 GB file
32K — · 128K —
Gemma 4 26B A4B IT
18.4 GB18.9 GB file
32K 19.3 GB · 128K 22.6 GB
Q5_K_L
Gemma 2 9B IT
7.4 GB6.9 GB file
32K — · 128K —
Gemma 4 26B A4B IT
19.4 GB19.5 GB file
32K 20.3 GB · 128K 23.6 GB
BF16
Gemma 2 9B IT
20.3 GB18.5 GB file
32K — · 128K —
Gemma 4 26B A4B IT
52.3 GB50.5 GB file
32K 53.2 GB · 128K 56.5 GB
Gemma 2 9B IT
Ollama · Q4_K_M
ollama run hf.co/bartowski/gemma-2-9b-it-GGUF:Q4_K_MGemma 4 26B A4B IT
Ollama · Q4_K_M
ollama run hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:Q4_K_M| Spec | Gemma 2 9B IT | Gemma 4 26B A4B IT |
|---|---|---|
| Publisher | ||
| Parameters | 9.2B | 25.8B |
| Active parameters | — | 4.4B per token |
| Architecture | — | Gemma4ForConditionalGeneration |
| Context | 8K tokens | 256K tokens |
| Modalities | Chat | Vision, Function-calling |
| License | Gemma Terms | Apache 2.0 |
| Released | Jun 2024 | Mar 2026 |
Frequently Asked Questions
Which is better, Gemma 2 9B IT or Gemma 4 26B A4B IT?
Gemma 4 26B A4B IT leads llmrun Score 105.8 to 68.0; both fit 24 GB at Q4_K_M; Gemma 4 26B A4B IT is 1.6× faster on RTX 4090 (~171 vs ~107 tok/s). Choose Gemma 2 9B IT for fits an 8 GB GPU and lighter on memory; choose Gemma 4 26B A4B IT for higher llmrun Score and 1.6× faster on RTX 4090.
Which needs less VRAM, Gemma 2 9B IT or Gemma 4 26B A4B IT?
At Q4_K_M, Gemma 2 9B IT requires 6.1 GB while Gemma 4 26B A4B IT needs 16.1 GB, making Gemma 2 9B IT the easier model to run on your local setup.
Which is faster on RTX 4090?
Estimated decode speed on RTX 4090 is about 107 tok/s for Gemma 2 9B IT (Q4_K_M) and 171 tok/s for Gemma 4 26B A4B IT (Q4_K_M), so Gemma 4 26B A4B IT is faster. Estimates, ±20%.
Can I run Gemma 2 9B IT or Gemma 4 26B A4B IT on a 16 GB GPU?
Gemma 2 9B IT fits at Q4_K_M; Gemma 4 26B A4B IT fits at Q4_1.
Which has a longer context window, Gemma 2 9B IT or Gemma 4 26B A4B IT?
Gemma 2 9B IT supports 8,192 tokens and Gemma 4 26B A4B IT supports 262,144 tokens.