Llama 3.1 8B Instruct vs GPT OSS 20B
GPT OSS 20B leads llmrun Score 96.2 to 62.5; both fit 24 GB at Q4_K_M; GPT OSS 20B is 1.5× faster on RTX 4090 (~190 vs ~124 tok/s).
Model A · Meta
Llama 3.1 8B Instruct8.0B · 128K context · Llama 3.1 Community · Jul 2024
Model B · OpenAI
GPT OSS 20B20.9B · 4.2B active · 128K context · Apache 2.0 · Aug 2025
Choose Llama 3.1 8B Instruct if you want…
Fits an 8 GB GPU
Q4_K_M · 7.9 GB; GPT OSS 20B needs 6.3 GB at its smallest quant
Lighter on memory
5.3 vs 12.9 GB at Q4_K_M
Choose GPT OSS 20B if you want…
Higher llmrun Score
96.2 vs 62.5
Stronger at coding
100.9 vs 55.9
Stronger at science
92.4 vs 55.5
Ahead on the benchmarks
10 of 10 shared boards
1.5× faster on RTX 4090
~190 vs ~124 tok/s
More permissive license
Apache 2.0 vs Llama 3.1 Community
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
Llama 3.1 8B Instruct
Q4_K_M · ~33 tok/s
7.9 GB · up to 16Kmore headroom
GPT OSS 20B
IQ2_M · ~103 tok/s
7.6 GB · up to 32K
12 GB
RTX 3060 12GB · 12 GB tier
Llama 3.1 8B Instruct
Q4_K_M · ~44 tok/s
7.9 GB · up to 32Kmore headroom
GPT OSS 20B
IQ4_XS · ~89 tok/s
11.8 GB · up to 16K
16 GB
RTX 5060 Ti 16GB · 16 GB tier
Llama 3.1 8B Instruct
Q4_K_M · ~55 tok/s
7.9 GB · up to 32K
GPT OSS 20B
Q4_K_M · ~98 tok/s
13.1 GB · up to 128Kfaster
24 GBreference
RTX 4090 · 24 GB tier
Llama 3.1 8B Instruct
Q4_K_M · ~124 tok/s
7.9 GB · up to 64K
GPT OSS 20B
Q4_K_M · ~190 tok/s
13.1 GB · up to 128Kfaster
32 GB
RTX 5090 · 32 GB tier
Llama 3.1 8B Instruct
Q4_K_M · ~220 tok/s
7.9 GB · up to 128K
GPT OSS 20B
Q4_K_M · ~282 tok/s
13.1 GB · up to 128Kfaster
48 GB
RTX A6000 · 48 GB tier
Llama 3.1 8B Instruct
Q4_K_M · ~94 tok/s
7.9 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
Llama 3.1 8B Instruct
Q4_K_M · ~16 tok/s
7.9 GB · up to 128K
GPT OSS 20B
Q4_K_M · ~28 tok/s
13.1 GB · up to 128Kfaster
Mac 64 GB
Mac Studio M4 Max · Macs
Llama 3.1 8B Instruct
Q4_K_M · ~72 tok/s
7.9 GB · up to 128K
GPT OSS 20B
Q4_K_M · ~86 tok/s
13.1 GB · up to 128Kfaster
Mac 128 GB
Mac Studio M4 Max · Macs
Llama 3.1 8B Instruct
Q4_K_M · ~72 tok/s
7.9 GB · up to 128K
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
Llama 3.1 8B Instruct
GPT OSS 20B
Coding
Llama 3.1 8B Instruct
GPT OSS 20B
Science
Llama 3.1 8B Instruct
GPT OSS 20B
Reasoning
Llama 3.1 8B Instruct
GPT OSS 20B
Llama 3.1 8B Instruct · #88 of 92 open models · #31 of 34 that fit 24 GB
GPT OSS 20B · #58 of 92 open models · #15 of 34 that fit 24 GB
Benchmarks
10 shared boards: Llama 3.1 8B Instruct leads 0, GPT OSS 20B leads 10 · Benchmarks imported Oct 2026
Llama 3.1 8B Instruct
27.0%#86/97 open
IndependentEpoch AI · Jul 2024
GPT OSS 20B
60.8%#41/97 open
IndependentEpoch AI · Aug 2025
Llama 3.1 8B Instruct
1211.3#141/186 open
ArenaLMArena · Oct 2026
GPT OSS 20B
1317.3#96/186 open
ArenaLMArena · Oct 2026
Llama 3.1 8B Instruct
1.7%#76/85 open
IndependentEpoch AI · Jul 2024
GPT OSS 20B
65.3%#33/85 open
IndependentEpoch AI · Aug 2025
Llama 3.1 8B Instruct
44.3%#87/144 open
IndependentTIGER-Lab
GPT OSS 20B
73.6%#33/144 open
IndependentTIGER-Lab
Llama 3.1 8B Instruct
13.2%#64/65 open
Lab-reportedEpoch AI · Jul 2024
GPT OSS 20B
34.4%#47/65 open
Lab-reportedEpoch AI · Aug 2025
Llama 3.1 8B Instruct
1.7%#46/46 open
IndependentEpoch AI · Jul 2024
GPT OSS 20B
40.9%#21/46 open
IndependentEpoch AI · Aug 2025
Llama 3.1 8B Instruct
0.0%#57/67 open
IndependentEpoch AI · Jul 2024
GPT OSS 20B
4.0%#33/67 open
IndependentEpoch AI · Aug 2025
Llama 3.1 8B Instruct
0.0%#52/65 open
Lab-reportedEpoch AI · Jul 2024
GPT OSS 20B
1.4%#30/65 open
Lab-reportedEpoch AI · Aug 2025
Llama 3.1 8B Instruct
50.9%#59/68 open
Lab-reportedEpoch AI · Jul 2024
GPT OSS 20B
68.0%#34/68 open
Lab-reportedEpoch AI · Aug 2025
Llama 3.1 8B Instruct
5.4%#51/54 open
Lab-reportedEpoch AI · Jul 2024
GPT OSS 20B
14.5%#43/54 open
Lab-reportedEpoch AI · Aug 2025
8 more boards (other shared and single-model boards)
Only GPT OSS 20B (2)
- Terminal-Bench3.4%
- ALE-Bench566.0
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
Llama 3.1 8B Instruct
3.8 GB3.2 GB file
32K 9.3 GB · 128K 26.9 GB
GPT OSS 20B
9.3 GB11.5 GB file
32K 9.8 GB · 128K 11.5 GB
Q3_K_S
Llama 3.1 8B Instruct
3.9 GB3.7 GB file
32K 9.4 GB · 128K 27.0 GB
GPT OSS 20B
9.5 GB11.5 GB file
32K 10.0 GB · 128K 11.7 GB
Q3_K_M
Llama 3.1 8B Instruct
4.3 GB4.0 GB file
32K 9.8 GB · 128K 27.4 GB
GPT OSS 20B
10.6 GB11.5 GB file
32K 11.1 GB · 128K 12.8 GB
Q4_0
Llama 3.1 8B Instruct
4.4 GB4.7 GB file
32K 9.9 GB · 128K 27.5 GB
GPT OSS 20B
10.8 GB11.5 GB file
32K 11.3 GB · 128K 13.0 GB
Q4_K_M
Llama 3.1 8B Instruct
5.3 GB4.9 GB file
32K 10.8 GB · 128K 28.4 GB
GPT OSS 20B
12.9 GB11.6 GB file
32K 13.4 GB · 128K 15.1 GB
Q5_K_M
Llama 3.1 8B Instruct
6.3 GB5.7 GB file
32K 11.8 GB · 128K 29.4 GB
GPT OSS 20B
15.3 GB11.7 GB file
32K 15.8 GB · 128K 17.5 GB
Q6_K
Llama 3.1 8B Instruct
7.3 GB6.6 GB file
32K 12.8 GB · 128K 30.4 GB
GPT OSS 20B
17.6 GB12.0 GB file
32K 18.1 GB · 128K 19.8 GB
Q8_0
Llama 3.1 8B Instruct
8.8 GB8.5 GB file
32K 14.3 GB · 128K 32.0 GB
GPT OSS 20B
21.3 GB~20.9 GB file
32K 21.8 GB · 128K 23.5 GB
20 more quants
IQ2_XXS
Llama 3.1 8B Instruct
2.4 GB2.5 GB file
32K 7.9 GB · 128K 25.6 GB
GPT OSS 20B
6.1 GB~5.8 GB file
32K 6.6 GB · 128K 8.3 GB
IQ2_XS
Llama 3.1 8B Instruct
2.7 GB2.6 GB file
32K 8.2 GB · 128K 25.8 GB
GPT OSS 20B
6.7 GB~6.3 GB file
32K 7.2 GB · 128K 8.9 GB
IQ2_S
Llama 3.1 8B Instruct
2.8 GB2.8 GB file
32K 8.3 GB · 128K 25.9 GB
GPT OSS 20B
6.9 GB~6.5 GB file
32K 7.4 GB · 128K 9.1 GB
IQ2_M
Llama 3.1 8B Instruct
3.0 GB2.9 GB file
32K 8.5 GB · 128K 26.1 GB
GPT OSS 20B
7.4 GB~7.1 GB file
32K 7.9 GB · 128K 9.6 GB
IQ3_XXS
Llama 3.1 8B Instruct
3.4 GB3.3 GB file
32K 8.9 GB · 128K 26.5 GB
GPT OSS 20B
8.5 GB11.6 GB file
32K 9.0 GB · 128K 10.7 GB
Q2_K_S
Llama 3.1 8B Instruct
3.5 GB3.0 GB file
32K 9.0 GB · 128K 26.7 GB
GPT OSS 20B
8.7 GB12.1 GB file
32K 9.2 GB · 128K 10.9 GB
IQ3_XS
Llama 3.1 8B Instruct
3.6 GB3.5 GB file
32K 9.1 GB · 128K 26.8 GB
GPT OSS 20B
9.0 GB11.6 GB file
32K 9.5 GB · 128K 11.2 GB
IQ3_S
Llama 3.1 8B Instruct
3.8 GB3.7 GB file
32K 9.3 GB · 128K 26.9 GB
GPT OSS 20B
9.3 GB12.1 GB file
32K 9.8 GB · 128K 11.5 GB
IQ3_M
Llama 3.1 8B Instruct
4.0 GB3.8 GB file
32K 9.5 GB · 128K 27.1 GB
GPT OSS 20B
9.8 GB11.6 GB file
32K 10.3 GB · 128K 12.0 GB
Q3_K_L
Llama 3.1 8B Instruct
4.5 GB4.3 GB file
32K 10.0 GB · 128K 27.7 GB
GPT OSS 20B
11.1 GB11.5 GB file
32K 11.6 GB · 128K 13.3 GB
IQ4_XS
Llama 3.1 8B Instruct
4.8 GB4.4 GB file
32K 10.3 GB · 128K 27.9 GB
GPT OSS 20B
11.6 GB11.6 GB file
32K 12.1 GB · 128K 13.8 GB
IQ4_NL
Llama 3.1 8B Instruct
5.0 GB4.7 GB file
32K 10.5 GB · 128K 28.1 GB
GPT OSS 20B
12.1 GB11.6 GB file
32K 12.6 GB · 128K 14.3 GB
Q4_1
Llama 3.1 8B Instruct
5.0 GB5.1 GB file
32K 10.5 GB · 128K 28.1 GB
GPT OSS 20B
12.1 GB11.6 GB file
32K 12.6 GB · 128K 14.3 GB
Q4_K_S
Llama 3.1 8B Instruct
5.0 GB4.7 GB file
32K 10.5 GB · 128K 28.1 GB
GPT OSS 20B
12.1 GB11.6 GB file
32K 12.6 GB · 128K 14.3 GB
Q4_K_L
Llama 3.1 8B Instruct
5.4 GB5.3 GB file
32K 10.9 GB · 128K 28.5 GB
GPT OSS 20B
13.2 GB11.9 GB file
32K 13.7 GB · 128K 15.4 GB
Q5_0
Llama 3.1 8B Instruct
5.5 GB5.6 GB file
32K 11.0 GB · 128K 28.6 GB
GPT OSS 20B
not listed
Q5_1
Llama 3.1 8B Instruct
6.1 GB6.1 GB file
32K 11.6 GB · 128K 29.2 GB
GPT OSS 20B
not listed
Q5_K_S
Llama 3.1 8B Instruct
6.1 GB5.6 GB file
32K 11.6 GB · 128K 29.2 GB
GPT OSS 20B
14.8 GB11.7 GB file
32K 15.3 GB · 128K 17.0 GB
Q5_K_L
Llama 3.1 8B Instruct
6.4 GB6.1 GB file
32K 11.9 GB · 128K 29.5 GB
GPT OSS 20B
15.5 GB11.9 GB file
32K 16.0 GB · 128K 17.7 GB
BF16
Llama 3.1 8B Instruct
17.7 GB16.1 GB file
32K 23.2 GB · 128K 40.8 GB
GPT OSS 20B
42.2 GB~41.8 GB file
32K 42.7 GB · 128K 44.4 GB
Llama 3.1 8B Instruct
Ollama · Q4_K_M
ollama run hf.co/bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_MGPT OSS 20B
Ollama · Q4_K_M
ollama run hf.co/unsloth/gpt-oss-20b-GGUF:Q4_K_M| Spec | Llama 3.1 8B Instruct | GPT OSS 20B |
|---|---|---|
| Publisher | Meta | OpenAI |
| Parameters | 8.0B | 20.9B |
| Active parameters | — | 4.2B per token |
| Architecture | — | GptOssForCausalLM |
| Context | 128K tokens | 128K tokens |
| Modalities | Chat, Function-calling | Chat, Function-calling |
| License | Llama 3.1 Community | Apache 2.0 |
| Released | Jul 2024 | Aug 2025 |
Frequently Asked Questions
Which is better, Llama 3.1 8B Instruct or GPT OSS 20B?
GPT OSS 20B leads llmrun Score 96.2 to 62.5; both fit 24 GB at Q4_K_M; GPT OSS 20B is 1.5× faster on RTX 4090 (~190 vs ~124 tok/s). Choose Llama 3.1 8B Instruct for fits an 8 GB GPU and lighter on memory; choose GPT OSS 20B for higher llmrun Score and stronger at coding.
Which needs less VRAM, Llama 3.1 8B Instruct or GPT OSS 20B?
At Q4_K_M, Llama 3.1 8B Instruct requires 5.3 GB while GPT OSS 20B needs 12.9 GB, making Llama 3.1 8B Instruct the easier model to run on your local setup.
Which is faster on RTX 4090?
Estimated decode speed on RTX 4090 is about 124 tok/s for Llama 3.1 8B Instruct (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 Llama 3.1 8B Instruct or GPT OSS 20B on a 16 GB GPU?
Llama 3.1 8B Instruct fits at Q4_K_M; GPT OSS 20B fits at Q4_K_M.
Which has a longer context window, Llama 3.1 8B Instruct or GPT OSS 20B?
Llama 3.1 8B Instruct supports 131,072 tokens and GPT OSS 20B supports 131,072 tokens.