GPT OSS 20B vs QwQ 32B
GPT OSS 20B and QwQ 32B match in llmrun Score, with values of 96.2 versus 96.1; 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 · OpenAI
GPT OSS 20B20.9B · 4.2B active · 128K context · Apache 2.0 · Aug 2025
Model B · Alibaba
QwQ 32B32.8B · 40K context · Apache 2.0 · Mar 2025
Choose GPT OSS 20B if you want…
Fits a 12 GB GPU
IQ4_XS · 11.8 GB; QwQ 32B needs 13.6 GB at its smallest quant
5.9× faster on RTX 4090
~190 vs ~32 tok/s
Lighter on memory
12.9 vs 20.5 GB at Q4_K_M
Longer context window
128K vs 40K tokens
Newer release
Aug 2025 vs Mar 2025
Choose QwQ 32B if you want…
Also does reasoning
GPT OSS 20B 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
GPT OSS 20B
IQ2_M · ~103 tok/s
7.6 GB · up to 32Kfits
QwQ 32B
Doesn't fit
smallest quant needs 13.6 GB
12 GB
RTX 3060 12GB · 12 GB tier
GPT OSS 20B
IQ4_XS · ~89 tok/s
11.8 GB · up to 16Kfits
QwQ 32B
Doesn't fit
smallest quant needs 13.6 GB
16 GB
RTX 5060 Ti 16GB · 16 GB tier
GPT OSS 20B
Q4_K_M · ~98 tok/s
13.1 GB · up to 128Kmore headroom
QwQ 32B
IQ2_M · ~25 tok/s
15.7 GB · up to 16K
24 GBreference
RTX 4090 · 24 GB tier
GPT OSS 20B
Q4_K_M · ~190 tok/s
13.1 GB · up to 128Kmore headroom
QwQ 32B
Q4_K_M · ~32 tok/stight
24.3 GB · up to 8K
32 GB
RTX 5090 · 32 GB tier
GPT OSS 20B
Q4_K_M · ~282 tok/s
13.1 GB · up to 128Kfaster
QwQ 32B
Q4_K_M · ~57 tok/s
24.3 GB · up to 40K
48 GB
RTX A6000 · 48 GB tier
GPT OSS 20B
Q4_K_M · ~154 tok/s
13.1 GB · up to 128Kfaster
QwQ 32B
Q4_K_M · ~24 tok/s
24.3 GB · up to 40K
Mac 32 GB
Mac Mini M4 · Macs
GPT OSS 20B
Q4_K_M · ~28 tok/s
13.1 GB · up to 128Kfaster
QwQ 32B
Q4_K_M · ~4 tok/s
24.3 GB · up to 16K
Mac 64 GB
Mac Studio M4 Max · Macs
GPT OSS 20B
Q4_K_M · ~86 tok/s
13.1 GB · up to 128Kfaster
QwQ 32B
Q4_K_M · ~19 tok/s
24.3 GB · up to 40K
Mac 128 GB
Mac Studio M4 Max · Macs
GPT OSS 20B
Q4_K_M · ~86 tok/s
13.1 GB · up to 128Kfaster
QwQ 32B
Q4_K_M · ~19 tok/s
24.3 GB · up to 40K
Reference GPU: RTX 4090. Tinted cell = the better pick on that machine (fits, more headroom, or at least 10% faster).
Overall
GPT OSS 20B
QwQ 32B
Coding
GPT OSS 20B
QwQ 32B
no data
Science
GPT OSS 20B
QwQ 32B
no data
Reasoning
GPT OSS 20B
QwQ 32B
no data
GPT OSS 20B · #58 of 92 open models · #15 of 34 that fit 24 GB
QwQ 32B · #59 of 92 open models · #16 of 34 that fit 24 GB
GPT OSS 20B
60.8%#41/97 open
IndependentEpoch AI · Aug 2025
QwQ 32B
65.3%#37/97 open
IndependentEpoch AI · Mar 2025
GPT OSS 20B
1317.3#96/186 open
ArenaLMArena · Oct 2026
QwQ 32B
1335.7#84/186 open
ArenaLMArena · Oct 2026
GPT OSS 20B
65.3%#33/85 open
IndependentEpoch AI · Aug 2025
QwQ 32B
59.2%#37/85 open
IndependentEpoch AI · Mar 2025
GPT OSS 20B
73.6%#33/144 open
IndependentTIGER-Lab
QwQ 32B
69.1%#40/144 open
IndependentTIGER-Lab
GPT OSS 20B
4.0%#33/67 open
IndependentEpoch AI · Aug 2025
QwQ 32B
5.0%#32/67 open
IndependentEpoch AI · Mar 2025
9 more boards (other shared and single-model boards)
Only GPT OSS 20B (7)
Only QwQ 32B (2)
- Aider Polyglot20.9%
- Fiction.LiveBench83.3%
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
GPT OSS 20B
9.3 GB11.5 GB file
32K 9.8 GB · 128K 11.5 GB
QwQ 32B
14.8 GB12.3 GB file
32K 22.8 GB · 128K —
Q3_K_S
GPT OSS 20B
9.5 GB11.5 GB file
32K 10.0 GB · 128K 11.7 GB
QwQ 32B
15.2 GB14.4 GB file
32K 23.2 GB · 128K —
Q3_K_M
GPT OSS 20B
10.6 GB11.5 GB file
32K 11.1 GB · 128K 12.8 GB
QwQ 32B
16.8 GB15.9 GB file
32K 24.9 GB · 128K —
Q4_0
GPT OSS 20B
10.8 GB11.5 GB file
32K 11.3 GB · 128K 13.0 GB
QwQ 32B
17.2 GB18.7 GB file
32K 25.3 GB · 128K —
Q4_K_M
GPT OSS 20B
12.9 GB11.6 GB file
32K 13.4 GB · 128K 15.1 GB
QwQ 32B
20.5 GB19.9 GB file
32K 28.6 GB · 128K —
Q5_K_M
GPT OSS 20B
15.3 GB11.7 GB file
32K 15.8 GB · 128K 17.5 GB
QwQ 32B
24.2 GB23.3 GB file
32K 32.2 GB · 128K —
Q6_K
GPT OSS 20B
17.6 GB12.0 GB file
32K 18.1 GB · 128K 19.8 GB
QwQ 32B
27.9 GB26.9 GB file
32K 35.9 GB · 128K —
Q8_0
GPT OSS 20B
21.3 GB~20.9 GB file
32K 21.8 GB · 128K 23.5 GB
QwQ 32B
33.6 GB34.8 GB file
32K 41.7 GB · 128K —
20 more quants
IQ2_XXS
GPT OSS 20B
6.1 GB~5.8 GB file
32K 6.6 GB · 128K 8.3 GB
QwQ 32B
9.9 GB9.0 GB file
32K 17.9 GB · 128K —
IQ2_XS
GPT OSS 20B
6.7 GB~6.3 GB file
32K 7.2 GB · 128K 8.9 GB
QwQ 32B
10.7 GB10.0 GB file
32K 18.7 GB · 128K —
IQ2_S
GPT OSS 20B
6.9 GB~6.5 GB file
32K 7.4 GB · 128K 9.1 GB
QwQ 32B
11.1 GB10.4 GB file
32K 19.1 GB · 128K —
IQ2_M
GPT OSS 20B
7.4 GB~7.1 GB file
32K 7.9 GB · 128K 9.6 GB
QwQ 32B
11.9 GB11.3 GB file
32K 19.9 GB · 128K —
IQ3_XXS
GPT OSS 20B
8.5 GB11.6 GB file
32K 9.0 GB · 128K 10.7 GB
QwQ 32B
13.5 GB12.8 GB file
32K 21.6 GB · 128K —
Q2_K_S
GPT OSS 20B
8.7 GB12.1 GB file
32K 9.2 GB · 128K 10.9 GB
QwQ 32B
13.9 GB11.5 GB file
32K 22.0 GB · 128K —
IQ3_XS
GPT OSS 20B
9.0 GB11.6 GB file
32K 9.5 GB · 128K 11.2 GB
QwQ 32B
14.4 GB13.7 GB file
32K 22.4 GB · 128K —
IQ3_S
GPT OSS 20B
9.3 GB12.1 GB file
32K 9.8 GB · 128K 11.5 GB
QwQ 32B
14.8 GB14.4 GB file
32K 22.8 GB · 128K —
IQ3_M
GPT OSS 20B
9.8 GB11.6 GB file
32K 10.3 GB · 128K 12.0 GB
QwQ 32B
15.6 GB14.8 GB file
32K 23.6 GB · 128K —
Q3_K_L
GPT OSS 20B
11.1 GB11.5 GB file
32K 11.6 GB · 128K 13.3 GB
QwQ 32B
17.6 GB17.2 GB file
32K 25.7 GB · 128K —
IQ4_XS
GPT OSS 20B
11.6 GB11.6 GB file
32K 12.1 GB · 128K 13.8 GB
QwQ 32B
18.5 GB17.7 GB file
32K 26.5 GB · 128K —
IQ4_NL
GPT OSS 20B
12.1 GB11.6 GB file
32K 12.6 GB · 128K 14.3 GB
QwQ 32B
19.3 GB18.7 GB file
32K 27.3 GB · 128K —
Q4_1
GPT OSS 20B
12.1 GB11.6 GB file
32K 12.6 GB · 128K 14.3 GB
QwQ 32B
19.3 GB20.6 GB file
32K 27.3 GB · 128K —
Q4_K_S
GPT OSS 20B
12.1 GB11.6 GB file
32K 12.6 GB · 128K 14.3 GB
QwQ 32B
19.3 GB18.8 GB file
32K 27.3 GB · 128K —
Q4_K_L
GPT OSS 20B
13.2 GB11.9 GB file
32K 13.7 GB · 128K 15.4 GB
QwQ 32B
20.9 GB20.4 GB file
32K 29.0 GB · 128K —
Q5_0
GPT OSS 20B
not listed
QwQ 32B
21.3 GB22.6 GB file
32K 29.4 GB · 128K —
Q5_1
GPT OSS 20B
not listed
QwQ 32B
23.4 GB24.6 GB file
32K 31.4 GB · 128K —
Q5_K_S
GPT OSS 20B
14.8 GB11.7 GB file
32K 15.3 GB · 128K 17.0 GB
QwQ 32B
23.4 GB22.6 GB file
32K 31.4 GB · 128K —
Q5_K_L
GPT OSS 20B
15.5 GB11.9 GB file
32K 16.0 GB · 128K 17.7 GB
QwQ 32B
24.6 GB23.7 GB file
32K 32.6 GB · 128K —
BF16
GPT OSS 20B
42.2 GB~41.8 GB file
32K 42.7 GB · 128K 44.4 GB
QwQ 32B
66.4 GB65.5 GB file
32K 74.4 GB · 128K —
GPT OSS 20B
Ollama · Q4_K_M
ollama run hf.co/unsloth/gpt-oss-20b-GGUF:Q4_K_MQwQ 32B
Ollama · Q4_K_M
ollama run hf.co/MaziyarPanahi/QwQ-32B-GGUF:Q4_K_M| Spec | GPT OSS 20B | QwQ 32B |
|---|---|---|
| Publisher | OpenAI | Alibaba |
| Parameters | 20.9B | 32.8B |
| Active parameters | 4.2B per token | — |
| Architecture | GptOssForCausalLM | Qwen2ForCausalLM |
| Context | 128K tokens | 40K tokens |
| Modalities | Chat, Function-calling | Chat, Reasoning, Function-calling |
| License | Apache 2.0 | Apache 2.0 |
| Released | Aug 2025 | Mar 2025 |
Frequently Asked Questions
Which is better, GPT OSS 20B or QwQ 32B?
GPT OSS 20B and QwQ 32B match in llmrun Score, with values of 96.2 versus 96.1; both fit 24 GB at Q4_K_M; GPT OSS 20B is 5.9× faster on RTX 4090 (~190 vs ~32 tok/s). Choose GPT OSS 20B for fits a 12 GB GPU and 5.9× faster on RTX 4090; choose QwQ 32B for also does reasoning.
Which needs less VRAM, GPT OSS 20B or QwQ 32B?
At Q4_K_M, GPT OSS 20B requires 12.9 GB while QwQ 32B needs 20.5 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 190 tok/s for GPT OSS 20B (Q4_K_M) and 32 tok/s for QwQ 32B (Q4_K_M), so GPT OSS 20B is faster. Estimates, ±20%.
Can I run GPT OSS 20B or QwQ 32B on a 16 GB GPU?
GPT OSS 20B fits at Q4_K_M; QwQ 32B fits at IQ2_M.
Which has a longer context window, GPT OSS 20B or QwQ 32B?
GPT OSS 20B supports 131,072 tokens and QwQ 32B supports 40,960 tokens.