DeepSeek R1 Distill Qwen 32B vs GPT OSS 20B
DeepSeek R1 Distill Qwen 32B and GPT OSS 20B match in llmrun Score, with values of 97.0 versus 96.2; 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 · DeepSeek
DeepSeek R1 Distill Qwen 32B32.8B · 128K context · MIT · Jan 2025
Model B · OpenAI
GPT OSS 20B20.9B · 4.2B active · 128K context · Apache 2.0 · Aug 2025
Choose DeepSeek R1 Distill Qwen 32B if you want…
Also does reasoning
GPT OSS 20B doesn't list it
Choose GPT OSS 20B if you want…
Fits a 12 GB GPU
IQ4_XS · 11.8 GB; DeepSeek R1 Distill Qwen 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
Newer release
Aug 2025 vs Jan 2025
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
DeepSeek R1 Distill Qwen 32B
Doesn't fit
smallest quant needs 13.6 GB
GPT OSS 20B
IQ2_M · ~103 tok/s
7.6 GB · up to 32Kfits
12 GB
RTX 3060 12GB · 12 GB tier
DeepSeek R1 Distill Qwen 32B
Doesn't fit
smallest quant needs 13.6 GB
GPT OSS 20B
IQ4_XS · ~89 tok/s
11.8 GB · up to 16Kfits
16 GB
RTX 5060 Ti 16GB · 16 GB tier
DeepSeek R1 Distill Qwen 32B
IQ2_M · ~25 tok/s
15.7 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
DeepSeek R1 Distill Qwen 32B
Q4_K_M · ~32 tok/stight
24.3 GB · up to 8K
GPT OSS 20B
Q4_K_M · ~190 tok/s
13.1 GB · up to 128Kmore headroom
32 GB
RTX 5090 · 32 GB tier
DeepSeek R1 Distill Qwen 32B
Q4_K_M · ~57 tok/s
24.3 GB · up to 32K
GPT OSS 20B
Q4_K_M · ~282 tok/s
13.1 GB · up to 128Kfaster
48 GB
RTX A6000 · 48 GB tier
DeepSeek R1 Distill Qwen 32B
Q4_K_M · ~24 tok/s
24.3 GB · up to 64K
GPT OSS 20B
Q4_K_M · ~154 tok/s
13.1 GB · up to 128Kfaster
Mac 32 GB
Mac Mini M4 · Macs
DeepSeek R1 Distill Qwen 32B
Q4_K_M · ~4 tok/s
24.3 GB · up to 16K
GPT OSS 20B
Q4_K_M · ~28 tok/s
13.1 GB · up to 128Kfaster
Mac 64 GB
Mac Studio M4 Max · Macs
DeepSeek R1 Distill Qwen 32B
Q4_K_M · ~19 tok/s
24.3 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
DeepSeek R1 Distill Qwen 32B
Q4_K_M · ~19 tok/s
24.3 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
DeepSeek R1 Distill Qwen 32B
GPT OSS 20B
Coding
DeepSeek R1 Distill Qwen 32B
no data
GPT OSS 20B
Science
DeepSeek R1 Distill Qwen 32B
no data
GPT OSS 20B
Reasoning
DeepSeek R1 Distill Qwen 32B
no data
GPT OSS 20B
DeepSeek R1 Distill Qwen 32B · #55 of 92 open models · #13 of 34 that fit 24 GB
GPT OSS 20B · #58 of 92 open models · #15 of 34 that fit 24 GB
Benchmarks
3 shared boards: DeepSeek R1 Distill Qwen 32B leads 1, GPT OSS 20B leads 2 · Benchmarks imported Oct 2026
DeepSeek R1 Distill Qwen 32B
64.1%#38/97 open
IndependentEpoch AI · Jan 2025
GPT OSS 20B
60.8%#41/97 open
IndependentEpoch AI · Aug 2025
DeepSeek R1 Distill Qwen 32B
55.6%#41/85 open
IndependentEpoch AI · Jan 2025
GPT OSS 20B
65.3%#33/85 open
IndependentEpoch AI · Aug 2025
DeepSeek R1 Distill Qwen 32B
1.0%#41/67 open
IndependentEpoch AI · Jan 2025
GPT OSS 20B
4.0%#33/67 open
IndependentEpoch AI · Aug 2025
10 more boards (other shared and single-model boards)
Only DeepSeek R1 Distill Qwen 32B (1)
- BALROG19.5%
Only GPT OSS 20B (9)
- LMArena Text1317.3
- Terminal-Bench3.4%
- MMLU-Pro73.6%
- SciCode34.4%
- WeirdML40.9%
- CritPt1.4%
- DTBench68.0%
- LMCA14.5%
- 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
DeepSeek R1 Distill Qwen 32B
14.8 GB12.3 GB file
32K 22.8 GB · 128K 48.6 GB
GPT OSS 20B
9.3 GB11.5 GB file
32K 9.8 GB · 128K 11.5 GB
Q3_K_S
DeepSeek R1 Distill Qwen 32B
15.2 GB14.4 GB file
32K 23.2 GB · 128K 49.0 GB
GPT OSS 20B
9.5 GB11.5 GB file
32K 10.0 GB · 128K 11.7 GB
Q3_K_M
DeepSeek R1 Distill Qwen 32B
16.8 GB15.9 GB file
32K 24.9 GB · 128K 50.6 GB
GPT OSS 20B
10.6 GB11.5 GB file
32K 11.1 GB · 128K 12.8 GB
Q4_0
DeepSeek R1 Distill Qwen 32B
17.2 GB18.7 GB file
32K 25.3 GB · 128K 51.0 GB
GPT OSS 20B
10.8 GB11.5 GB file
32K 11.3 GB · 128K 13.0 GB
Q4_K_M
DeepSeek R1 Distill Qwen 32B
20.5 GB19.9 GB file
32K 28.6 GB · 128K 54.3 GB
GPT OSS 20B
12.9 GB11.6 GB file
32K 13.4 GB · 128K 15.1 GB
Q5_K_M
DeepSeek R1 Distill Qwen 32B
24.2 GB23.3 GB file
32K 32.2 GB · 128K 58.0 GB
GPT OSS 20B
15.3 GB11.7 GB file
32K 15.8 GB · 128K 17.5 GB
Q6_K
DeepSeek R1 Distill Qwen 32B
27.9 GB26.9 GB file
32K 35.9 GB · 128K 61.7 GB
GPT OSS 20B
17.6 GB12.0 GB file
32K 18.1 GB · 128K 19.8 GB
Q8_0
DeepSeek R1 Distill Qwen 32B
33.6 GB34.8 GB file
32K 41.7 GB · 128K 67.4 GB
GPT OSS 20B
21.3 GB~20.9 GB file
32K 21.8 GB · 128K 23.5 GB
19 more quants
IQ2_XXS
DeepSeek R1 Distill Qwen 32B
9.9 GB9.0 GB file
32K 17.9 GB · 128K 43.7 GB
GPT OSS 20B
6.1 GB~5.8 GB file
32K 6.6 GB · 128K 8.3 GB
IQ2_XS
DeepSeek R1 Distill Qwen 32B
10.7 GB10.0 GB file
32K 18.7 GB · 128K 44.5 GB
GPT OSS 20B
6.7 GB~6.3 GB file
32K 7.2 GB · 128K 8.9 GB
IQ2_S
DeepSeek R1 Distill Qwen 32B
11.1 GB10.4 GB file
32K 19.1 GB · 128K 44.9 GB
GPT OSS 20B
6.9 GB~6.5 GB file
32K 7.4 GB · 128K 9.1 GB
IQ2_M
DeepSeek R1 Distill Qwen 32B
11.9 GB11.3 GB file
32K 19.9 GB · 128K 45.7 GB
GPT OSS 20B
7.4 GB~7.1 GB file
32K 7.9 GB · 128K 9.6 GB
IQ3_XXS
DeepSeek R1 Distill Qwen 32B
13.5 GB12.8 GB file
32K 21.6 GB · 128K 47.4 GB
GPT OSS 20B
8.5 GB11.6 GB file
32K 9.0 GB · 128K 10.7 GB
Q2_K_S
DeepSeek R1 Distill Qwen 32B
13.9 GB11.5 GB file
32K 22.0 GB · 128K 47.8 GB
GPT OSS 20B
8.7 GB12.1 GB file
32K 9.2 GB · 128K 10.9 GB
IQ3_XS
DeepSeek R1 Distill Qwen 32B
14.4 GB13.7 GB file
32K 22.4 GB · 128K 48.2 GB
GPT OSS 20B
9.0 GB11.6 GB file
32K 9.5 GB · 128K 11.2 GB
IQ3_S
DeepSeek R1 Distill Qwen 32B
14.8 GB14.4 GB file
32K 22.8 GB · 128K 48.6 GB
GPT OSS 20B
9.3 GB12.1 GB file
32K 9.8 GB · 128K 11.5 GB
IQ3_M
DeepSeek R1 Distill Qwen 32B
15.6 GB14.8 GB file
32K 23.6 GB · 128K 49.4 GB
GPT OSS 20B
9.8 GB11.6 GB file
32K 10.3 GB · 128K 12.0 GB
Q3_K_L
DeepSeek R1 Distill Qwen 32B
17.6 GB17.2 GB file
32K 25.7 GB · 128K 51.5 GB
GPT OSS 20B
11.1 GB11.5 GB file
32K 11.6 GB · 128K 13.3 GB
IQ4_XS
DeepSeek R1 Distill Qwen 32B
18.5 GB17.7 GB file
32K 26.5 GB · 128K 52.3 GB
GPT OSS 20B
11.6 GB11.6 GB file
32K 12.1 GB · 128K 13.8 GB
IQ4_NL
DeepSeek R1 Distill Qwen 32B
19.3 GB18.7 GB file
32K 27.3 GB · 128K 53.1 GB
GPT OSS 20B
12.1 GB11.6 GB file
32K 12.6 GB · 128K 14.3 GB
Q4_1
DeepSeek R1 Distill Qwen 32B
19.3 GB20.6 GB file
32K 27.3 GB · 128K 53.1 GB
GPT OSS 20B
12.1 GB11.6 GB file
32K 12.6 GB · 128K 14.3 GB
Q4_K_S
DeepSeek R1 Distill Qwen 32B
19.3 GB18.8 GB file
32K 27.3 GB · 128K 53.1 GB
GPT OSS 20B
12.1 GB11.6 GB file
32K 12.6 GB · 128K 14.3 GB
Q4_K_L
DeepSeek R1 Distill Qwen 32B
20.9 GB20.4 GB file
32K 29.0 GB · 128K 54.7 GB
GPT OSS 20B
13.2 GB11.9 GB file
32K 13.7 GB · 128K 15.4 GB
Q5_0
DeepSeek R1 Distill Qwen 32B
21.3 GB22.6 GB file
32K 29.4 GB · 128K 55.1 GB
GPT OSS 20B
not listed
Q5_K_S
DeepSeek R1 Distill Qwen 32B
23.4 GB22.6 GB file
32K 31.4 GB · 128K 57.2 GB
GPT OSS 20B
14.8 GB11.7 GB file
32K 15.3 GB · 128K 17.0 GB
Q5_K_L
DeepSeek R1 Distill Qwen 32B
24.6 GB23.7 GB file
32K 32.6 GB · 128K 58.4 GB
GPT OSS 20B
15.5 GB11.9 GB file
32K 16.0 GB · 128K 17.7 GB
BF16
DeepSeek R1 Distill Qwen 32B
66.4 GB65.5 GB file
32K 74.4 GB · 128K 100 GB
GPT OSS 20B
42.2 GB~41.8 GB file
32K 42.7 GB · 128K 44.4 GB
DeepSeek R1 Distill Qwen 32B
Ollama · Q4_K_M
ollama run hf.co/unsloth/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q4_K_MGPT OSS 20B
Ollama · Q4_K_M
ollama run hf.co/unsloth/gpt-oss-20b-GGUF:Q4_K_M| Spec | DeepSeek R1 Distill Qwen 32B | GPT OSS 20B |
|---|---|---|
| Publisher | DeepSeek | OpenAI |
| Parameters | 32.8B | 20.9B |
| Active parameters | — | 4.2B per token |
| Architecture | Qwen2ForCausalLM | GptOssForCausalLM |
| Context | 128K tokens | 128K tokens |
| Modalities | Chat, Reasoning, Function-calling | Chat, Function-calling |
| License | MIT | Apache 2.0 |
| Released | Jan 2025 | Aug 2025 |
Frequently Asked Questions
Which is better, DeepSeek R1 Distill Qwen 32B or GPT OSS 20B?
DeepSeek R1 Distill Qwen 32B and GPT OSS 20B match in llmrun Score, with values of 97.0 versus 96.2; both fit 24 GB at Q4_K_M; GPT OSS 20B is 5.9× faster on RTX 4090 (~190 vs ~32 tok/s). Choose DeepSeek R1 Distill Qwen 32B for also does reasoning; choose GPT OSS 20B for fits a 12 GB GPU and 5.9× faster on RTX 4090.
Which needs less VRAM, DeepSeek R1 Distill Qwen 32B or GPT OSS 20B?
At Q4_K_M, DeepSeek R1 Distill Qwen 32B requires 20.5 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 DeepSeek R1 Distill Qwen 32B (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 DeepSeek R1 Distill Qwen 32B or GPT OSS 20B on a 16 GB GPU?
DeepSeek R1 Distill Qwen 32B fits at IQ2_M; GPT OSS 20B fits at Q4_K_M.
Which has a longer context window, DeepSeek R1 Distill Qwen 32B or GPT OSS 20B?
DeepSeek R1 Distill Qwen 32B supports 131,072 tokens and GPT OSS 20B supports 131,072 tokens.