Gemma 4 31B IT vs GPT OSS 20B
Gemma 4 31B IT leads llmrun Score 106.7 to 96.4; both fit 24 GB at Q4_K_M; GPT OSS 20B is 5.9× faster on RTX 4090 (~190 vs ~32 tok/s).
Model A · Google
Gemma 4 31B IT31.3B · 256K context · Apache 2.0 · Mar 2026
Model B · OpenAI
GPT OSS 20B20.9B · 4.2B active · 128K context · Apache 2.0 · Aug 2025
Choose Gemma 4 31B IT if you want…
Higher llmrun Score
106.7 vs 96.4
Stronger at reasoning
111.1 vs 91.3
Stronger at science
105.2 vs 93.1
Ahead on the benchmarks
7 of 8 shared boards
Longer context window
256K vs 128K tokens
Also does vision
GPT OSS 20B doesn't list it
Choose GPT OSS 20B if you want…
Fits a 12 GB GPU
IQ4_XS · 11.8 GB; Gemma 4 31B IT needs 11.5 GB at its smallest quant
5.9× faster on RTX 4090
~190 vs ~32 tok/s
Lighter on memory
12.9 vs 20.4 GB at Q4_K_M
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
GPT OSS 20B
IQ2_M · ~103 tok/s
7.6 GB · up to 32Kfits
12 GB
RTX 3060 12GB · 12 GB tier
Gemma 4 31B IT
IQ2_XXS · ~23 tok/s
11.5 GB · up to 16K
GPT OSS 20B
IQ4_XS · ~89 tok/s
11.8 GB · up to 16Kbetter quant
16 GB
RTX 5060 Ti 16GB · 16 GB tier
Gemma 4 31B IT
IQ3_XS · ~20 tok/s
15.8 GB · up to 16K
GPT OSS 20B
Q4_K_M · ~98 tok/s
13.1 GB · up to 128Kmore headroom
24 GBreference
RTX 4090 · 24 GB tier
Gemma 4 31B IT
Q4_K_M · ~32 tok/s
21.7 GB · up to 32K
GPT OSS 20B
Q4_K_M · ~190 tok/s
13.1 GB · up to 128Kfaster
32 GB
RTX 5090 · 32 GB tier
Gemma 4 31B IT
Q4_K_M · ~57 tok/s
21.7 GB · up to 64K
GPT OSS 20B
Q4_K_M · ~282 tok/s
13.1 GB · up to 128Kfaster
48 GB
RTX A6000 · 48 GB tier
Gemma 4 31B IT
Q4_K_M · ~25 tok/s
21.7 GB · up to 128K
GPT OSS 20B
Q4_K_M · ~154 tok/s
13.1 GB · up to 128Kfaster
Mac 32 GB
Mac Mini M4 · Macs
Gemma 4 31B IT
Q4_K_M · ~4 tok/s
21.7 GB · up to 64K
GPT OSS 20B
Q4_K_M · ~28 tok/s
13.1 GB · up to 128Kfaster
Mac 64 GB
Mac Studio M4 Max · Macs
Gemma 4 31B IT
Q4_K_M · ~19 tok/s
21.7 GB · up to 256K
GPT OSS 20B
Q4_K_M · ~86 tok/s
13.1 GB · up to 128Kfaster
Mac 128 GB
Mac Studio M4 Max · Macs
Gemma 4 31B IT
Q4_K_M · ~19 tok/s
21.7 GB · up to 256K
GPT OSS 20B
Q4_K_M · ~86 tok/s
13.1 GB · up to 128Kfaster
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
GPT OSS 20B
Coding
Gemma 4 31B IT
GPT OSS 20B
Science
Gemma 4 31B IT
GPT OSS 20B
Reasoning
Gemma 4 31B IT
GPT OSS 20B
Gemma 4 31B IT · #42 of 106 open models · #4 of 36 that fit 24 GB
GPT OSS 20B · #69 of 106 open models · #16 of 36 that fit 24 GB
Benchmarks
8 shared boards: Gemma 4 31B IT leads 7, GPT OSS 20B leads 0 · Benchmarks imported Nov 2026
Gemma 4 31B IT
75.8%#30/100 open
IndependentEpoch AI · Apr 2026
GPT OSS 20B
60.8%#44/100 open
IndependentEpoch AI · Aug 2025
Gemma 4 31B IT
73.3%#28/88 open
IndependentEpoch AI · Apr 2026
GPT OSS 20B
65.3%#36/88 open
IndependentEpoch AI · Aug 2025
Gemma 4 31B IT
45.5%#25/72 open
Lab-reportedEpoch AI · Apr 2026
GPT OSS 20B
38.9%#41/72 open
Lab-reportedEpoch AI · Aug 2025
Gemma 4 31B IT
52.3%#9/47 open
IndependentEpoch AI · Apr 2026
GPT OSS 20B
40.9%#22/47 open
IndependentEpoch AI · Aug 2025
Gemma 4 31B IT
925.5#17/48 open
Lab-reportedEpoch AI · Apr 2026
GPT OSS 20B
566.0#35/48 open
Lab-reportedEpoch AI · Aug 2025
Gemma 4 31B IT
1.4%#35/84 open
Lab-reportedEpoch AI · Apr 2026
GPT OSS 20B
1.4%#36/84 open
Lab-reportedEpoch AI · Aug 2025
Gemma 4 31B IT
82.7%#20/70 open
Lab-reportedEpoch AI · Apr 2026
GPT OSS 20B
68.0%#36/70 open
Lab-reportedEpoch AI · Aug 2025
Gemma 4 31B IT
39.3%#9/56 open
Lab-reportedEpoch AI · Apr 2026
GPT OSS 20B
14.5%#45/56 open
Lab-reportedEpoch AI · Aug 2025
14 more boards (other shared and single-model boards)
Gemma 4 31B IT
1452.3#14/188 open
ArenaLMArena · Oct 2026
GPT OSS 20B
1317.3#98/188 open
ArenaLMArena · Oct 2026
Only Gemma 4 31B IT (11)
Only GPT OSS 20B (2)
- Terminal-Bench3.4%
- MMLU-Pro73.6%
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
GPT OSS 20B
9.3 GB11.5 GB file
32K 9.8 GB · 128K 11.5 GB
Q3_K_S
Gemma 4 31B IT
15.3 GB13.2 GB file
32K 18.7 GB · 128K 31.4 GB
GPT OSS 20B
9.5 GB11.5 GB file
32K 10.0 GB · 128K 11.7 GB
Q3_K_M
Gemma 4 31B IT
16.9 GB14.7 GB file
32K 20.3 GB · 128K 33.0 GB
GPT OSS 20B
10.6 GB11.5 GB file
32K 11.1 GB · 128K 12.8 GB
Q4_0
Gemma 4 31B IT
17.3 GB17.3 GB file
32K 20.7 GB · 128K 33.4 GB
GPT OSS 20B
10.8 GB11.5 GB file
32K 11.3 GB · 128K 13.0 GB
Q4_K_M
Gemma 4 31B IT
20.4 GB18.3 GB file
32K 23.8 GB · 128K 36.5 GB
GPT OSS 20B
12.9 GB11.6 GB file
32K 13.4 GB · 128K 15.1 GB
Q5_K_M
Gemma 4 31B IT
23.9 GB21.7 GB file
32K 27.3 GB · 128K 40.0 GB
GPT OSS 20B
15.3 GB11.7 GB file
32K 15.8 GB · 128K 17.5 GB
Q6_K
Gemma 4 31B IT
27.4 GB25.2 GB file
32K 30.9 GB · 128K 43.5 GB
GPT OSS 20B
17.6 GB12.0 GB file
32K 18.1 GB · 128K 19.8 GB
Q8_0
Gemma 4 31B IT
32.9 GB32.6 GB file
32K 36.3 GB · 128K 49.0 GB
GPT OSS 20B
21.3 GB~20.9 GB file
32K 21.8 GB · 128K 23.5 GB
19 more quants
IQ2_XXS
Gemma 4 31B IT
10.2 GB8.5 GB file
32K 13.7 GB · 128K 26.3 GB
GPT OSS 20B
6.1 GB~5.8 GB file
32K 6.6 GB · 128K 8.3 GB
IQ2_XS
Gemma 4 31B IT
11.0 GB11.5 GB file
32K 14.4 GB · 128K 27.1 GB
GPT OSS 20B
6.7 GB~6.3 GB file
32K 7.2 GB · 128K 8.9 GB
IQ2_S
Gemma 4 31B IT
11.4 GB12.1 GB file
32K 14.8 GB · 128K 27.5 GB
GPT OSS 20B
6.9 GB~6.5 GB file
32K 7.4 GB · 128K 9.1 GB
IQ2_M
Gemma 4 31B IT
12.2 GB10.8 GB file
32K 15.6 GB · 128K 28.3 GB
GPT OSS 20B
7.4 GB~7.1 GB file
32K 7.9 GB · 128K 9.6 GB
IQ3_XXS
Gemma 4 31B IT
13.7 GB11.8 GB file
32K 17.2 GB · 128K 29.9 GB
GPT OSS 20B
8.5 GB11.6 GB file
32K 9.0 GB · 128K 10.7 GB
Q2_K_S
Gemma 4 31B IT
14.1 GB11.0 GB file
32K 17.6 GB · 128K 30.3 GB
GPT OSS 20B
8.7 GB12.1 GB file
32K 9.2 GB · 128K 10.9 GB
IQ3_XS
Gemma 4 31B IT
14.5 GB13.8 GB file
32K 18.0 GB · 128K 30.6 GB
GPT OSS 20B
9.0 GB11.6 GB file
32K 9.5 GB · 128K 11.2 GB
IQ3_S
Gemma 4 31B IT
14.9 GB13.8 GB file
32K 18.4 GB · 128K 31.0 GB
GPT OSS 20B
9.3 GB12.1 GB file
32K 9.8 GB · 128K 11.5 GB
IQ3_M
Gemma 4 31B IT
15.7 GB15.1 GB file
32K 19.1 GB · 128K 31.8 GB
GPT OSS 20B
9.8 GB11.6 GB file
32K 10.3 GB · 128K 12.0 GB
Q3_K_L
Gemma 4 31B IT
17.7 GB16.8 GB file
32K 21.1 GB · 128K 33.8 GB
GPT OSS 20B
11.1 GB11.5 GB file
32K 11.6 GB · 128K 13.3 GB
IQ4_XS
Gemma 4 31B IT
18.4 GB16.4 GB file
32K 21.9 GB · 128K 34.6 GB
GPT OSS 20B
11.6 GB11.6 GB file
32K 12.1 GB · 128K 13.8 GB
IQ4_NL
Gemma 4 31B IT
19.2 GB17.3 GB file
32K 22.7 GB · 128K 35.3 GB
GPT OSS 20B
12.1 GB11.6 GB file
32K 12.6 GB · 128K 14.3 GB
Q4_1
Gemma 4 31B IT
19.2 GB19.1 GB file
32K 22.7 GB · 128K 35.3 GB
GPT OSS 20B
12.1 GB11.6 GB file
32K 12.6 GB · 128K 14.3 GB
Q4_K_S
Gemma 4 31B IT
19.2 GB17.4 GB file
32K 22.7 GB · 128K 35.3 GB
GPT OSS 20B
12.1 GB11.6 GB file
32K 12.6 GB · 128K 14.3 GB
Q4_K_L
Gemma 4 31B IT
20.8 GB19.9 GB file
32K 24.2 GB · 128K 36.9 GB
GPT OSS 20B
13.2 GB11.9 GB file
32K 13.7 GB · 128K 15.4 GB
Q5_0
Gemma 4 31B IT
21.2 GB21.3 GB file
32K 24.6 GB · 128K 37.3 GB
GPT OSS 20B
not listed
Q5_K_S
Gemma 4 31B IT
23.1 GB21.1 GB file
32K 26.6 GB · 128K 39.2 GB
GPT OSS 20B
14.8 GB11.7 GB file
32K 15.3 GB · 128K 17.0 GB
Q5_K_L
Gemma 4 31B IT
24.3 GB23.0 GB file
32K 27.7 GB · 128K 40.4 GB
GPT OSS 20B
15.5 GB11.9 GB file
32K 16.0 GB · 128K 17.7 GB
BF16
Gemma 4 31B IT
64.2 GB61.4 GB file
32K 67.6 GB · 128K 80.3 GB
GPT OSS 20B
42.2 GB~41.8 GB file
32K 42.7 GB · 128K 44.4 GB
Gemma 4 31B IT
Ollama · Q4_K_M
ollama run hf.co/unsloth/gemma-4-31B-it-GGUF:Q4_K_MGPT OSS 20B
Ollama · Q4_K_M
ollama run hf.co/unsloth/gpt-oss-20b-GGUF:Q4_K_M| Spec | Gemma 4 31B IT | GPT OSS 20B |
|---|---|---|
| Publisher | OpenAI | |
| Parameters | 31.3B | 20.9B |
| Active parameters | — | 4.2B per token |
| Architecture | Gemma4ForConditionalGeneration | GptOssForCausalLM |
| Context | 256K tokens | 128K tokens |
| Modalities | Vision, Function-calling | Chat, Function-calling |
| License | Apache 2.0 | Apache 2.0 |
| Released | Mar 2026 | Aug 2025 |
Frequently Asked Questions
Which is better, Gemma 4 31B IT or GPT OSS 20B?
Gemma 4 31B IT leads llmrun Score 106.7 to 96.4; both fit 24 GB at Q4_K_M; GPT OSS 20B is 5.9× faster on RTX 4090 (~190 vs ~32 tok/s). Choose Gemma 4 31B IT for higher llmrun Score and stronger at reasoning; choose GPT OSS 20B for fits a 12 GB GPU and 5.9× faster on RTX 4090.
Which needs less VRAM, Gemma 4 31B IT or GPT OSS 20B?
At Q4_K_M, Gemma 4 31B IT requires 20.4 GB while GPT OSS 20B needs 12.9 GB, making GPT OSS 20B 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 190 tok/s for GPT OSS 20B (Q4_K_M), so GPT OSS 20B is faster. Estimates, ±20%.
Can I run Gemma 4 31B IT or GPT OSS 20B on a 16 GB GPU?
Gemma 4 31B IT fits at IQ3_XS; GPT OSS 20B fits at Q4_K_M.
Which has a longer context window, Gemma 4 31B IT or GPT OSS 20B?
Gemma 4 31B IT supports 262,144 tokens and GPT OSS 20B supports 131,072 tokens.