Qwen2.5 32B Instruct vs Qwen3.6 35B A3B
Qwen3.6 35B A3B leads llmrun Score 106.8 to 80.4; both fit 24 GB at Q4_K_M; Qwen3.6 35B A3B is 4.7× faster on RTX 4090 (~151 vs ~32 tok/s).
Model A · Alibaba
Qwen2.5 32B Instruct32.8B · 32K context · Apache 2.0 · Sep 2024
Model B · Alibaba
Qwen3.6 35B A3B36.0B · 4.7B active · 256K context · Apache 2.0 · Apr 2026
Choose Qwen2.5 32B Instruct if you want…
Also does chat
Qwen3.6 35B A3B doesn't list it
Choose Qwen3.6 35B A3B if you want…
Higher llmrun Score
106.8 vs 80.4
4.7× faster on RTX 4090
~151 vs ~32 tok/s
Longer context window
256K vs 32K tokens
Also does vision
Qwen2.5 32B Instruct doesn't list it
Newer release
Apr 2026 vs Sep 2024
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
Qwen2.5 32B Instruct
Doesn't fit
smallest quant needs 13.6 GB
Qwen3.6 35B A3B
Doesn't fit
smallest quant needs 10.4 GB
12 GB
RTX 3060 12GB · 12 GB tier
Qwen2.5 32B Instruct
Doesn't fit
smallest quant needs 13.6 GB
Qwen3.6 35B A3B
IQ2_S · ~114 tok/s
11.7 GB · up to 32Kfits
16 GB
RTX 5060 Ti 16GB · 16 GB tier
Qwen2.5 32B Instruct
IQ2_M · ~25 tok/s
15.7 GB · up to 16K
Qwen3.6 35B A3B
Q2_K · ~108 tok/s
15.7 GB · up to 32K
24 GBreference
RTX 4090 · 24 GB tier
Qwen2.5 32B Instruct
Q4_K_M · ~32 tok/stight
24.3 GB · up to 8K
Qwen3.6 35B A3B
Q4_K_M · ~151 tok/s
22 GB · up to 128Kmore headroom
32 GB
RTX 5090 · 32 GB tier
Qwen2.5 32B Instruct
Q4_K_M · ~57 tok/s
24.3 GB · up to 32K
Qwen3.6 35B A3B
Q4_K_M · ~213 tok/s
22 GB · up to 256Kfaster
48 GB
RTX A6000 · 48 GB tier
Qwen2.5 32B Instruct
Q4_K_M · ~24 tok/s
24.3 GB · up to 32K
Qwen3.6 35B A3B
Q4_K_M · ~125 tok/s
22 GB · up to 256Kfaster
Mac 32 GB
Mac Mini M4 · Macs
Qwen2.5 32B Instruct
Q4_K_M · ~4 tok/s
24.3 GB · up to 16K
Qwen3.6 35B A3B
Q4_K_M · ~24 tok/s
22 GB · up to 256Kfaster
Mac 64 GB
Mac Studio M4 Max · Macs
Qwen2.5 32B Instruct
Q4_K_M · ~19 tok/s
24.3 GB · up to 32K
Qwen3.6 35B A3B
Q4_K_M · ~64 tok/s
22 GB · up to 256Kfaster
Mac 128 GB
Mac Studio M4 Max · Macs
Qwen2.5 32B Instruct
Q4_K_M · ~19 tok/s
24.3 GB · up to 32K
Qwen3.6 35B A3B
Q4_K_M · ~64 tok/s
22 GB · up to 256Kfaster
Reference GPU: RTX 4090. Tinted cell = the better pick on that machine (fits, more headroom, or at least 10% faster).
Overall
Qwen2.5 32B Instruct
Qwen3.6 35B A3B
Coding
Qwen2.5 32B Instruct
no data
Qwen3.6 35B A3B
Math
Qwen2.5 32B Instruct
no data
Qwen3.6 35B A3B
Science
Qwen2.5 32B Instruct
no data
Qwen3.6 35B A3B
Reasoning
Qwen2.5 32B Instruct
no data
Qwen3.6 35B A3B
Qwen2.5 32B Instruct · #88 of 106 open models · #25 of 36 that fit 24 GB
Qwen3.6 35B A3B · #41 of 106 open models · #3 of 36 that fit 24 GB
Benchmarks
2 shared boards: Qwen2.5 32B Instruct leads 0, Qwen3.6 35B A3B leads 2 · Benchmarks imported Nov 2026
Qwen2.5 32B Instruct
46.1%#65/100 open
IndependentEpoch AI · Sep 2024
Qwen3.6 35B A3B
84.9%#23/100 open
IndependentEpoch AI · Apr 2026
Qwen2.5 32B Instruct
7.4%#67/88 open
IndependentEpoch AI · Sep 2024
Qwen3.6 35B A3B
86.7%#22/88 open
IndependentEpoch AI · Apr 2026
11 more boards (other shared and single-model boards)
Only Qwen2.5 32B Instruct (2)
- MMLU-Pro69.2%
- MATH Level 556.1%
Only Qwen3.6 35B A3B (9)
- FrontierMath20.3%
- Terminal-Bench24.6%
- SciCode36.6%
- WeirdML34.5%
- CritPt0.3%
- DTBench73.9%
- LMCA29.7%
- Mystery Game Puzzles22.0%
- Surface Evolver Bench44.4%
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
Qwen2.5 32B Instruct
14.8 GB12.3 GB file
32K 22.8 GB · 128K —
Qwen3.6 35B A3B
15.7 GB13.5 GB file
32K 15.9 GB · 128K 16.9 GB
Q3_K_S
Qwen2.5 32B Instruct
15.2 GB14.4 GB file
32K 23.2 GB · 128K —
Qwen3.6 35B A3B
16.1 GB15.4 GB file
32K 16.4 GB · 128K 17.4 GB
Q3_K_M
Qwen2.5 32B Instruct
16.8 GB15.9 GB file
32K 24.9 GB · 128K —
Qwen3.6 35B A3B
17.9 GB16.6 GB file
32K 18.2 GB · 128K 19.2 GB
Q4_0
Qwen2.5 32B Instruct
17.2 GB18.6 GB file
32K 25.3 GB · 128K —
Qwen3.6 35B A3B
18.4 GB19.8 GB file
32K 18.6 GB · 128K 19.6 GB
Q4_K_M
Qwen2.5 32B Instruct
20.5 GB19.9 GB file
32K 28.6 GB · 128K —
Qwen3.6 35B A3B
22.0 GB22.1 GB file
32K 22.2 GB · 128K 23.2 GB
Q5_K_M
Qwen2.5 32B Instruct
24.2 GB23.3 GB file
32K 32.2 GB · 128K —
Qwen3.6 35B A3B
26.0 GB26.5 GB file
32K 26.3 GB · 128K 27.3 GB
Q6_K
Qwen2.5 32B Instruct
27.9 GB26.9 GB file
32K 35.9 GB · 128K —
Qwen3.6 35B A3B
30.0 GB29.3 GB file
32K 30.3 GB · 128K 31.3 GB
Q8_0
Qwen2.5 32B Instruct
33.6 GB34.8 GB file
32K 41.7 GB · 128K —
Qwen3.6 35B A3B
36.3 GB36.9 GB file
32K 36.6 GB · 128K 37.6 GB
20 more quants
IQ2_XXS
Qwen2.5 32B Instruct
9.9 GB9.0 GB file
32K 17.9 GB · 128K —
Qwen3.6 35B A3B
10.3 GB10.8 GB file
32K 10.5 GB · 128K 11.5 GB
IQ2_XS
Qwen2.5 32B Instruct
10.7 GB10.0 GB file
32K 18.7 GB · 128K —
Qwen3.6 35B A3B
11.2 GB11.7 GB file
32K 11.4 GB · 128K 12.4 GB
IQ2_S
Qwen2.5 32B Instruct
11.1 GB10.4 GB file
32K 19.1 GB · 128K —
Qwen3.6 35B A3B
11.6 GB11.9 GB file
32K 11.9 GB · 128K 12.9 GB
IQ2_M
Qwen2.5 32B Instruct
11.9 GB11.3 GB file
32K 19.9 GB · 128K —
Qwen3.6 35B A3B
12.5 GB11.5 GB file
32K 12.8 GB · 128K 13.8 GB
IQ3_XXS
Qwen2.5 32B Instruct
13.5 GB12.8 GB file
32K 21.6 GB · 128K —
Qwen3.6 35B A3B
14.3 GB13.2 GB file
32K 14.6 GB · 128K 15.6 GB
Q2_K_S
Qwen2.5 32B Instruct
13.9 GB11.5 GB file
32K 22.0 GB · 128K —
Qwen3.6 35B A3B
14.8 GB12.2 GB file
32K 15.0 GB · 128K 16.0 GB
IQ3_XS
Qwen2.5 32B Instruct
14.4 GB13.7 GB file
32K 22.4 GB · 128K —
Qwen3.6 35B A3B
15.2 GB17.1 GB file
32K 15.5 GB · 128K 16.5 GB
IQ3_S
Qwen2.5 32B Instruct
14.8 GB14.4 GB file
32K 22.8 GB · 128K —
Qwen3.6 35B A3B
15.7 GB13.7 GB file
32K 15.9 GB · 128K 16.9 GB
IQ3_M
Qwen2.5 32B Instruct
15.6 GB14.8 GB file
32K 23.6 GB · 128K —
Qwen3.6 35B A3B
16.6 GB17.8 GB file
32K 16.8 GB · 128K 17.8 GB
Q3_K_L
Qwen2.5 32B Instruct
17.6 GB17.2 GB file
32K 25.7 GB · 128K —
Qwen3.6 35B A3B
18.8 GB17.8 GB file
32K 19.1 GB · 128K 20.1 GB
IQ4_XS
Qwen2.5 32B Instruct
18.5 GB17.7 GB file
32K 26.5 GB · 128K —
Qwen3.6 35B A3B
19.7 GB17.7 GB file
32K 20.0 GB · 128K 21.0 GB
IQ4_NL
Qwen2.5 32B Instruct
not listed
Qwen3.6 35B A3B
20.6 GB18.0 GB file
32K 20.9 GB · 128K 21.9 GB
Q4_1
Qwen2.5 32B Instruct
19.3 GB20.6 GB file
32K 27.3 GB · 128K —
Qwen3.6 35B A3B
20.6 GB22.9 GB file
32K 20.9 GB · 128K 21.9 GB
Q4_K_S
Qwen2.5 32B Instruct
19.3 GB18.8 GB file
32K 27.3 GB · 128K —
Qwen3.6 35B A3B
20.6 GB20.9 GB file
32K 20.9 GB · 128K 21.9 GB
Q4_K_L
Qwen2.5 32B Instruct
20.9 GB20.4 GB file
32K 29.0 GB · 128K —
Qwen3.6 35B A3B
22.4 GB22.7 GB file
32K 22.7 GB · 128K 23.7 GB
Q5_0
Qwen2.5 32B Instruct
21.3 GB22.6 GB file
32K 29.4 GB · 128K —
Qwen3.6 35B A3B
22.9 GB24.1 GB file
32K 23.1 GB · 128K 24.1 GB
Q5_1
Qwen2.5 32B Instruct
not listed
Qwen3.6 35B A3B
25.1 GB26.1 GB file
32K 25.4 GB · 128K 26.4 GB
Q5_K_S
Qwen2.5 32B Instruct
23.4 GB22.6 GB file
32K 31.4 GB · 128K —
Qwen3.6 35B A3B
25.1 GB24.9 GB file
32K 25.4 GB · 128K 26.4 GB
Q5_K_L
Qwen2.5 32B Instruct
24.6 GB23.7 GB file
32K 32.6 GB · 128K —
Qwen3.6 35B A3B
26.5 GB26.2 GB file
32K 26.7 GB · 128K 27.7 GB
BF16
Qwen2.5 32B Instruct
66.4 GB~65.5 GB file
32K 74.4 GB · 128K —
Qwen3.6 35B A3B
72.3 GB69.4 GB file
32K 72.5 GB · 128K 73.6 GB
Qwen2.5 32B Instruct
Ollama · Q4_K_M
ollama run hf.co/bartowski/Qwen2.5-32B-Instruct-GGUF:Q4_K_MQwen3.6 35B A3B
Ollama · Q4_K_M
ollama run hf.co/unsloth/Qwen3.6-35B-A3B-GGUF:Q4_K_M| Spec | Qwen2.5 32B Instruct | Qwen3.6 35B A3B |
|---|---|---|
| Publisher | Alibaba | Alibaba |
| Parameters | 32.8B | 36.0B |
| Active parameters | — | 4.7B per token |
| Architecture | Qwen2ForCausalLM | Qwen3_5MoeForConditionalGeneration |
| Context | 32K tokens | 256K tokens |
| Modalities | Chat, Function-calling | Vision, Function-calling |
| License | Apache 2.0 | Apache 2.0 |
| Released | Sep 2024 | Apr 2026 |
Frequently Asked Questions
Which is better, Qwen2.5 32B Instruct or Qwen3.6 35B A3B?
Qwen3.6 35B A3B leads llmrun Score 106.8 to 80.4; both fit 24 GB at Q4_K_M; Qwen3.6 35B A3B is 4.7× faster on RTX 4090 (~151 vs ~32 tok/s). Choose Qwen2.5 32B Instruct for also does chat; choose Qwen3.6 35B A3B for higher llmrun Score and 4.7× faster on RTX 4090.
Which needs less VRAM, Qwen2.5 32B Instruct or Qwen3.6 35B A3B?
At Q4_K_M, Qwen2.5 32B Instruct requires 20.5 GB while Qwen3.6 35B A3B needs 22.0 GB, making Qwen2.5 32B Instruct 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 Qwen2.5 32B Instruct (Q4_K_M) and 151 tok/s for Qwen3.6 35B A3B (Q4_K_M), so Qwen3.6 35B A3B is faster. Estimates, ±20%.
Can I run Qwen2.5 32B Instruct or Qwen3.6 35B A3B on a 16 GB GPU?
Qwen2.5 32B Instruct fits at IQ2_M; Qwen3.6 35B A3B fits at Q2_K.
Which has a longer context window, Qwen2.5 32B Instruct or Qwen3.6 35B A3B?
Qwen2.5 32B Instruct supports 32,768 tokens and Qwen3.6 35B A3B supports 262,144 tokens.