Gemma 4 31B IT vs Qwen3 30B A3B
Gemma 4 31B IT leads llmrun Score 106.7 to 93.9; both fit 24 GB at Q4_K_M; Qwen3 30B A3B is 5.4× faster on RTX 4090 (~173 vs ~32 tok/s).
Model A · Google
Gemma 4 31B IT31.3B · 256K context · Apache 2.0 · Mar 2026
Model B · Alibaba
Qwen3 30B A3B30.5B · 3.4B active · 40K context · Apache 2.0 · Apr 2025
Choose Gemma 4 31B IT if you want…
Higher llmrun Score
106.7 vs 93.9
Stronger at reasoning
111.1 vs 83.8
Ahead on the benchmarks
5 of 5 shared boards
Longer context window
256K vs 40K tokens
Also does vision
Qwen3 30B A3B doesn't list it
Newer release
Mar 2026 vs Apr 2025
Choose Qwen3 30B A3B if you want…
5.4× faster on RTX 4090
~173 vs ~32 tok/s
Also does chat
Gemma 4 31B IT doesn't list it
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 31B IT
Doesn't fit
smallest quant needs 11.5 GB
Qwen3 30B A3B
Doesn't fit
smallest quant needs 9.5 GB
12 GB
RTX 3060 12GB · 12 GB tier
Gemma 4 31B IT
IQ2_XXS · ~23 tok/s
11.5 GB · up to 16K
Qwen3 30B A3B
IQ2_M · ~130 tok/s
11.4 GB · up to 16K
16 GB
RTX 5060 Ti 16GB · 16 GB tier
Gemma 4 31B IT
IQ3_XS · ~20 tok/s
15.8 GB · up to 16K
Qwen3 30B A3B
Q3_K_M · ~119 tok/s
16 GB · up to 16K
24 GBreference
RTX 4090 · 24 GB tier
Gemma 4 31B IT
Q4_K_M · ~32 tok/s
21.7 GB · up to 32K
Qwen3 30B A3B
Q4_K_M · ~173 tok/s
19.4 GB · up to 40Kfaster
32 GB
RTX 5090 · 32 GB tier
Gemma 4 31B IT
Q4_K_M · ~57 tok/s
21.7 GB · up to 64K
Qwen3 30B A3B
Q4_K_M · ~227 tok/s
19.4 GB · up to 40Kfaster
48 GB
RTX A6000 · 48 GB tier
Gemma 4 31B IT
Q4_K_M · ~25 tok/s
21.7 GB · up to 128K
Qwen3 30B A3B
Q4_K_M · ~148 tok/s
19.4 GB · up to 40Kfaster
Mac 32 GB
Mac Mini M4 · Macs
Gemma 4 31B IT
Q4_K_M · ~4 tok/s
21.7 GB · up to 64K
Qwen3 30B A3B
Q4_K_M · ~29 tok/s
19.4 GB · up to 40Kfaster
Mac 64 GB
Mac Studio M4 Max · Macs
Gemma 4 31B IT
Q4_K_M · ~19 tok/s
21.7 GB · up to 256K
Qwen3 30B A3B
Q4_K_M · ~67 tok/s
19.4 GB · up to 40Kfaster
Mac 128 GB
Mac Studio M4 Max · Macs
Gemma 4 31B IT
Q4_K_M · ~19 tok/s
21.7 GB · up to 256K
Qwen3 30B A3B
Q4_K_M · ~67 tok/s
19.4 GB · up to 40Kfaster
Reference GPU: RTX 4090. Tinted cell = the better pick on that machine (fits, more headroom, or at least 10% faster).
Overall
Gemma 4 31B IT
Qwen3 30B A3B
Coding
Gemma 4 31B IT
Qwen3 30B A3B
no data
Science
Gemma 4 31B IT
Qwen3 30B A3B
no data
Reasoning
Gemma 4 31B IT
Qwen3 30B A3B
Gemma 4 31B IT · #42 of 106 open models · #4 of 36 that fit 24 GB
Qwen3 30B A3B · #74 of 106 open models · #18 of 36 that fit 24 GB
Benchmarks
5 shared boards: Gemma 4 31B IT leads 5, Qwen3 30B A3B leads 0 · Benchmarks imported Nov 2026
Gemma 4 31B IT
75.8%#30/100 open
IndependentEpoch AI · Apr 2026
Qwen3 30B A3B
61.7%#43/100 open
IndependentEpoch AI · Apr 2025
Gemma 4 31B IT
73.3%#28/88 open
IndependentEpoch AI · Apr 2026
Qwen3 30B A3B
62.8%#37/88 open
IndependentEpoch AI · Apr 2025
Gemma 4 31B IT
52.3%#9/47 open
IndependentEpoch AI · Apr 2026
Qwen3 30B A3B
29.8%#39/47 open
IndependentEpoch AI · Apr 2025
Gemma 4 31B IT
82.7%#20/70 open
Lab-reportedEpoch AI · Apr 2026
Qwen3 30B A3B
60.3%#49/70 open
Lab-reportedEpoch AI · Apr 2025
Gemma 4 31B IT
39.3%#9/56 open
Lab-reportedEpoch AI · Apr 2026
Qwen3 30B A3B
15.8%#42/56 open
Lab-reportedEpoch AI · Apr 2025
16 more boards (other shared and single-model boards)
Gemma 4 31B IT
1452.3#14/188 open
ArenaLMArena · Oct 2026
Qwen3 30B A3B
1326.7#91/188 open
ArenaLMArena · Oct 2026
Only Gemma 4 31B IT (14)
- LMArena WebDev1368.7
- SciCode45.5%
- SimpleQA10.4%
- CritPt1.4%
- ForecastBench61.3
- LiveBench 2026 Reasoning68.3
- LiveBench 2026 Browser4.0
- LiveBench 2026 Data Analysis53.3
- ALE-Bench925.5
- LiveBench 2026 Coding49.0
- LiveBench 2026 Long-Horizon13.3
- Surface Evolver Bench30.6%
- LiveBench 2026 Design58.4
- LiveBench 2026 Research44.4
Only Qwen3 30B A3B (1)
- Fiction.LiveBench40.6%
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 31B IT
14.9 GB12.6 GB file
32K 18.4 GB · 128K 31.0 GB
Qwen3 30B A3B
13.4 GB11.3 GB file
32K 14.9 GB · 128K —
Q3_K_S
Gemma 4 31B IT
15.3 GB13.2 GB file
32K 18.7 GB · 128K 31.4 GB
Qwen3 30B A3B
13.8 GB13.3 GB file
32K 15.3 GB · 128K —
Q3_K_M
Gemma 4 31B IT
16.9 GB14.7 GB file
32K 20.3 GB · 128K 33.0 GB
Qwen3 30B A3B
15.3 GB14.7 GB file
32K 16.8 GB · 128K —
Q4_0
Gemma 4 31B IT
17.3 GB17.3 GB file
32K 20.7 GB · 128K 33.4 GB
Qwen3 30B A3B
15.7 GB17.4 GB file
32K 17.2 GB · 128K —
Q4_K_M
Gemma 4 31B IT
20.4 GB18.3 GB file
32K 23.8 GB · 128K 36.5 GB
Qwen3 30B A3B
18.7 GB18.6 GB file
32K 20.2 GB · 128K —
Q5_K_M
Gemma 4 31B IT
23.9 GB21.7 GB file
32K 27.3 GB · 128K 40.0 GB
Qwen3 30B A3B
22.2 GB21.7 GB file
32K 23.7 GB · 128K —
Q6_K
Gemma 4 31B IT
27.4 GB25.2 GB file
32K 30.9 GB · 128K 43.5 GB
Qwen3 30B A3B
25.6 GB25.1 GB file
32K 27.1 GB · 128K —
Q8_0
Gemma 4 31B IT
32.9 GB32.6 GB file
32K 36.3 GB · 128K 49.0 GB
Qwen3 30B A3B
30.9 GB32.5 GB file
32K 32.4 GB · 128K —
19 more quants
IQ2_XXS
Gemma 4 31B IT
10.2 GB8.5 GB file
32K 13.7 GB · 128K 26.3 GB
Qwen3 30B A3B
8.8 GB10.4 GB file
32K 10.3 GB · 128K —
IQ2_XS
Gemma 4 31B IT
11.0 GB11.5 GB file
32K 14.4 GB · 128K 27.1 GB
Qwen3 30B A3B
9.6 GB9.1 GB file
32K 11.1 GB · 128K —
IQ2_S
Gemma 4 31B IT
11.4 GB12.1 GB file
32K 14.8 GB · 128K 27.5 GB
Qwen3 30B A3B
9.9 GB9.2 GB file
32K 11.5 GB · 128K —
IQ2_M
Gemma 4 31B IT
12.2 GB10.8 GB file
32K 15.6 GB · 128K 28.3 GB
Qwen3 30B A3B
10.7 GB10.9 GB file
32K 12.2 GB · 128K —
IQ3_XXS
Gemma 4 31B IT
13.7 GB11.8 GB file
32K 17.2 GB · 128K 29.9 GB
Qwen3 30B A3B
12.2 GB12.9 GB file
32K 13.7 GB · 128K —
Q2_K_S
Gemma 4 31B IT
14.1 GB11.0 GB file
32K 17.6 GB · 128K 30.3 GB
Qwen3 30B A3B
not listed
IQ3_XS
Gemma 4 31B IT
14.5 GB13.8 GB file
32K 18.0 GB · 128K 30.6 GB
Qwen3 30B A3B
13.0 GB12.7 GB file
32K 14.5 GB · 128K —
IQ3_S
Gemma 4 31B IT
14.9 GB13.8 GB file
32K 18.4 GB · 128K 31.0 GB
Qwen3 30B A3B
13.4 GB14.0 GB file
32K 14.9 GB · 128K —
IQ3_M
Gemma 4 31B IT
15.7 GB15.1 GB file
32K 19.1 GB · 128K 31.8 GB
Qwen3 30B A3B
14.1 GB14.1 GB file
32K 15.7 GB · 128K —
Q3_K_L
Gemma 4 31B IT
17.7 GB16.8 GB file
32K 21.1 GB · 128K 33.8 GB
Qwen3 30B A3B
16.1 GB15.9 GB file
32K 17.6 GB · 128K —
IQ4_XS
Gemma 4 31B IT
18.4 GB16.4 GB file
32K 21.9 GB · 128K 34.6 GB
Qwen3 30B A3B
16.8 GB16.4 GB file
32K 18.3 GB · 128K —
IQ4_NL
Gemma 4 31B IT
19.2 GB17.3 GB file
32K 22.7 GB · 128K 35.3 GB
Qwen3 30B A3B
17.6 GB17.3 GB file
32K 19.1 GB · 128K —
Q4_1
Gemma 4 31B IT
19.2 GB19.1 GB file
32K 22.7 GB · 128K 35.3 GB
Qwen3 30B A3B
17.6 GB19.2 GB file
32K 19.1 GB · 128K —
Q4_K_S
Gemma 4 31B IT
19.2 GB17.4 GB file
32K 22.7 GB · 128K 35.3 GB
Qwen3 30B A3B
17.6 GB17.5 GB file
32K 19.1 GB · 128K —
Q4_K_L
Gemma 4 31B IT
20.8 GB19.9 GB file
32K 24.2 GB · 128K 36.9 GB
Qwen3 30B A3B
19.1 GB18.9 GB file
32K 20.6 GB · 128K —
Q5_0
Gemma 4 31B IT
21.2 GB21.3 GB file
32K 24.6 GB · 128K 37.3 GB
Qwen3 30B A3B
19.5 GB21.1 GB file
32K 21.0 GB · 128K —
Q5_K_S
Gemma 4 31B IT
23.1 GB21.1 GB file
32K 26.6 GB · 128K 39.2 GB
Qwen3 30B A3B
21.4 GB21.1 GB file
32K 22.9 GB · 128K —
Q5_K_L
Gemma 4 31B IT
24.3 GB23.0 GB file
32K 27.7 GB · 128K 40.4 GB
Qwen3 30B A3B
22.5 GB21.9 GB file
32K 24.1 GB · 128K —
BF16
Gemma 4 31B IT
64.2 GB61.4 GB file
32K 67.6 GB · 128K 80.3 GB
Qwen3 30B A3B
61.5 GB61.1 GB file
32K 63.0 GB · 128K —
Gemma 4 31B IT
Ollama · Q4_K_M
ollama run hf.co/unsloth/gemma-4-31B-it-GGUF:Q4_K_MQwen3 30B A3B
Ollama · Q4_K_M
ollama run hf.co/Qwen/Qwen3-30B-A3B-GGUF:Q4_K_M| Spec | Gemma 4 31B IT | Qwen3 30B A3B |
|---|---|---|
| Publisher | Alibaba | |
| Parameters | 31.3B | 30.5B |
| Active parameters | — | 3.4B per token |
| Architecture | Gemma4ForConditionalGeneration | Qwen3MoeForCausalLM |
| Context | 256K tokens | 40K tokens |
| Modalities | Vision, Function-calling | Chat, Function-calling |
| License | Apache 2.0 | Apache 2.0 |
| Released | Mar 2026 | Apr 2025 |
Frequently Asked Questions
Which is better, Gemma 4 31B IT or Qwen3 30B A3B?
Gemma 4 31B IT leads llmrun Score 106.7 to 93.9; both fit 24 GB at Q4_K_M; Qwen3 30B A3B is 5.4× faster on RTX 4090 (~173 vs ~32 tok/s). Choose Gemma 4 31B IT for higher llmrun Score and stronger at reasoning; choose Qwen3 30B A3B for 5.4× faster on RTX 4090 and also does chat.
Which needs less VRAM, Gemma 4 31B IT or Qwen3 30B A3B?
At Q4_K_M, Gemma 4 31B IT requires 20.4 GB while Qwen3 30B A3B needs 18.7 GB, making Qwen3 30B A3B the easier model to run on your local setup.
Which is faster on RTX 4090?
Estimated decode speed on RTX 4090 is about 32 tok/s for Gemma 4 31B IT (Q4_K_M) and 173 tok/s for Qwen3 30B A3B (Q4_K_M), so Qwen3 30B A3B is faster. Estimates, ±20%.
Can I run Gemma 4 31B IT or Qwen3 30B A3B on a 16 GB GPU?
Gemma 4 31B IT fits at IQ3_XS; Qwen3 30B A3B fits at Q3_K_M.
Which has a longer context window, Gemma 4 31B IT or Qwen3 30B A3B?
Gemma 4 31B IT supports 262,144 tokens and Qwen3 30B A3B supports 40,960 tokens.