Qwen3.6 35B A3B vs QwQ 32B
Qwen3.6 35B A3B leads llmrun Score 106.8 to 96.2; 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
Qwen3.6 35B A3B36.0B · 4.7B active · 256K context · Apache 2.0 · Apr 2026
Model B · Alibaba
QwQ 32B32.8B · 40K context · Apache 2.0 · Mar 2025
Choose Qwen3.6 35B A3B if you want…
Higher llmrun Score
106.8 vs 96.2
4.7× faster on RTX 4090
~151 vs ~32 tok/s
Longer context window
256K vs 40K tokens
Also does vision
QwQ 32B doesn't list it
Newer release
Apr 2026 vs Mar 2025
Choose QwQ 32B if you want…
Also does chat, reasoning
Qwen3.6 35B A3B 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
Qwen3.6 35B A3B
Doesn't fit
smallest quant needs 10.4 GB
QwQ 32B
Doesn't fit
smallest quant needs 13.6 GB
12 GB
RTX 3060 12GB · 12 GB tier
Qwen3.6 35B A3B
IQ2_S · ~114 tok/s
11.7 GB · up to 32Kfits
QwQ 32B
Doesn't fit
smallest quant needs 13.6 GB
16 GB
RTX 5060 Ti 16GB · 16 GB tier
Qwen3.6 35B A3B
Q2_K · ~108 tok/s
15.7 GB · up to 32K
QwQ 32B
IQ2_M · ~25 tok/s
15.7 GB · up to 16K
24 GBreference
RTX 4090 · 24 GB tier
Qwen3.6 35B A3B
Q4_K_M · ~151 tok/s
22 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
Qwen3.6 35B A3B
Q4_K_M · ~213 tok/s
22 GB · up to 256Kfaster
QwQ 32B
Q4_K_M · ~57 tok/s
24.3 GB · up to 40K
48 GB
RTX A6000 · 48 GB tier
Qwen3.6 35B A3B
Q4_K_M · ~125 tok/s
22 GB · up to 256Kfaster
QwQ 32B
Q4_K_M · ~24 tok/s
24.3 GB · up to 40K
Mac 32 GB
Mac Mini M4 · Macs
Qwen3.6 35B A3B
Q4_K_M · ~24 tok/s
22 GB · up to 256Kfaster
QwQ 32B
Q4_K_M · ~4 tok/s
24.3 GB · up to 16K
Mac 64 GB
Mac Studio M4 Max · Macs
Qwen3.6 35B A3B
Q4_K_M · ~64 tok/s
22 GB · up to 256Kfaster
QwQ 32B
Q4_K_M · ~19 tok/s
24.3 GB · up to 40K
Mac 128 GB
Mac Studio M4 Max · Macs
Qwen3.6 35B A3B
Q4_K_M · ~64 tok/s
22 GB · up to 256Kfaster
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
Qwen3.6 35B A3B
QwQ 32B
Coding
Qwen3.6 35B A3B
QwQ 32B
no data
Math
Qwen3.6 35B A3B
QwQ 32B
no data
Science
Qwen3.6 35B A3B
QwQ 32B
no data
Reasoning
Qwen3.6 35B A3B
QwQ 32B
no data
Qwen3.6 35B A3B · #41 of 106 open models · #3 of 36 that fit 24 GB
QwQ 32B · #70 of 106 open models · #17 of 36 that fit 24 GB
Qwen3.6 35B A3B
84.9%#23/100 open
IndependentEpoch AI · Apr 2026
QwQ 32B
65.3%#40/100 open
IndependentEpoch AI · Mar 2025
Qwen3.6 35B A3B
86.7%#22/88 open
IndependentEpoch AI · Apr 2026
QwQ 32B
59.2%#40/88 open
IndependentEpoch AI · Mar 2025
13 more boards (other shared and single-model boards)
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%
Only QwQ 32B (4)
- LMArena Text1335.6
- MMLU-Pro69.1%
- 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
Qwen3.6 35B A3B
15.7 GB13.5 GB file
32K 15.9 GB · 128K 16.9 GB
QwQ 32B
14.8 GB12.3 GB file
32K 22.8 GB · 128K —
Q3_K_S
Qwen3.6 35B A3B
16.1 GB15.4 GB file
32K 16.4 GB · 128K 17.4 GB
QwQ 32B
15.2 GB14.4 GB file
32K 23.2 GB · 128K —
Q3_K_M
Qwen3.6 35B A3B
17.9 GB16.6 GB file
32K 18.2 GB · 128K 19.2 GB
QwQ 32B
16.8 GB15.9 GB file
32K 24.9 GB · 128K —
Q4_0
Qwen3.6 35B A3B
18.4 GB19.8 GB file
32K 18.6 GB · 128K 19.6 GB
QwQ 32B
17.2 GB18.7 GB file
32K 25.3 GB · 128K —
Q4_K_M
Qwen3.6 35B A3B
22.0 GB22.1 GB file
32K 22.2 GB · 128K 23.2 GB
QwQ 32B
20.5 GB19.9 GB file
32K 28.6 GB · 128K —
Q5_K_M
Qwen3.6 35B A3B
26.0 GB26.5 GB file
32K 26.3 GB · 128K 27.3 GB
QwQ 32B
24.2 GB23.3 GB file
32K 32.2 GB · 128K —
Q6_K
Qwen3.6 35B A3B
30.0 GB29.3 GB file
32K 30.3 GB · 128K 31.3 GB
QwQ 32B
27.9 GB26.9 GB file
32K 35.9 GB · 128K —
Q8_0
Qwen3.6 35B A3B
36.3 GB36.9 GB file
32K 36.6 GB · 128K 37.6 GB
QwQ 32B
33.6 GB34.8 GB file
32K 41.7 GB · 128K —
20 more quants
IQ2_XXS
Qwen3.6 35B A3B
10.3 GB10.8 GB file
32K 10.5 GB · 128K 11.5 GB
QwQ 32B
9.9 GB9.0 GB file
32K 17.9 GB · 128K —
IQ2_XS
Qwen3.6 35B A3B
11.2 GB11.7 GB file
32K 11.4 GB · 128K 12.4 GB
QwQ 32B
10.7 GB10.0 GB file
32K 18.7 GB · 128K —
IQ2_S
Qwen3.6 35B A3B
11.6 GB11.9 GB file
32K 11.9 GB · 128K 12.9 GB
QwQ 32B
11.1 GB10.4 GB file
32K 19.1 GB · 128K —
IQ2_M
Qwen3.6 35B A3B
12.5 GB11.5 GB file
32K 12.8 GB · 128K 13.8 GB
QwQ 32B
11.9 GB11.3 GB file
32K 19.9 GB · 128K —
IQ3_XXS
Qwen3.6 35B A3B
14.3 GB13.2 GB file
32K 14.6 GB · 128K 15.6 GB
QwQ 32B
13.5 GB12.8 GB file
32K 21.6 GB · 128K —
Q2_K_S
Qwen3.6 35B A3B
14.8 GB12.2 GB file
32K 15.0 GB · 128K 16.0 GB
QwQ 32B
13.9 GB11.5 GB file
32K 22.0 GB · 128K —
IQ3_XS
Qwen3.6 35B A3B
15.2 GB17.1 GB file
32K 15.5 GB · 128K 16.5 GB
QwQ 32B
14.4 GB13.7 GB file
32K 22.4 GB · 128K —
IQ3_S
Qwen3.6 35B A3B
15.7 GB13.7 GB file
32K 15.9 GB · 128K 16.9 GB
QwQ 32B
14.8 GB14.4 GB file
32K 22.8 GB · 128K —
IQ3_M
Qwen3.6 35B A3B
16.6 GB17.8 GB file
32K 16.8 GB · 128K 17.8 GB
QwQ 32B
15.6 GB14.8 GB file
32K 23.6 GB · 128K —
Q3_K_L
Qwen3.6 35B A3B
18.8 GB17.8 GB file
32K 19.1 GB · 128K 20.1 GB
QwQ 32B
17.6 GB17.2 GB file
32K 25.7 GB · 128K —
IQ4_XS
Qwen3.6 35B A3B
19.7 GB17.7 GB file
32K 20.0 GB · 128K 21.0 GB
QwQ 32B
18.5 GB17.7 GB file
32K 26.5 GB · 128K —
IQ4_NL
Qwen3.6 35B A3B
20.6 GB18.0 GB file
32K 20.9 GB · 128K 21.9 GB
QwQ 32B
19.3 GB18.7 GB file
32K 27.3 GB · 128K —
Q4_1
Qwen3.6 35B A3B
20.6 GB22.9 GB file
32K 20.9 GB · 128K 21.9 GB
QwQ 32B
19.3 GB20.6 GB file
32K 27.3 GB · 128K —
Q4_K_S
Qwen3.6 35B A3B
20.6 GB20.9 GB file
32K 20.9 GB · 128K 21.9 GB
QwQ 32B
19.3 GB18.8 GB file
32K 27.3 GB · 128K —
Q4_K_L
Qwen3.6 35B A3B
22.4 GB22.7 GB file
32K 22.7 GB · 128K 23.7 GB
QwQ 32B
20.9 GB20.4 GB file
32K 29.0 GB · 128K —
Q5_0
Qwen3.6 35B A3B
22.9 GB24.1 GB file
32K 23.1 GB · 128K 24.1 GB
QwQ 32B
21.3 GB22.6 GB file
32K 29.4 GB · 128K —
Q5_1
Qwen3.6 35B A3B
25.1 GB26.1 GB file
32K 25.4 GB · 128K 26.4 GB
QwQ 32B
23.4 GB24.6 GB file
32K 31.4 GB · 128K —
Q5_K_S
Qwen3.6 35B A3B
25.1 GB24.9 GB file
32K 25.4 GB · 128K 26.4 GB
QwQ 32B
23.4 GB22.6 GB file
32K 31.4 GB · 128K —
Q5_K_L
Qwen3.6 35B A3B
26.5 GB26.2 GB file
32K 26.7 GB · 128K 27.7 GB
QwQ 32B
24.6 GB23.7 GB file
32K 32.6 GB · 128K —
BF16
Qwen3.6 35B A3B
72.3 GB69.4 GB file
32K 72.5 GB · 128K 73.6 GB
QwQ 32B
66.4 GB65.5 GB file
32K 74.4 GB · 128K —
Qwen3.6 35B A3B
Ollama · Q4_K_M
ollama run hf.co/unsloth/Qwen3.6-35B-A3B-GGUF:Q4_K_MQwQ 32B
Ollama · Q4_K_M
ollama run hf.co/Qwen/QwQ-32B-GGUF:Q4_K_M| Spec | Qwen3.6 35B A3B | QwQ 32B |
|---|---|---|
| Publisher | Alibaba | Alibaba |
| Parameters | 36.0B | 32.8B |
| Active parameters | 4.7B per token | — |
| Architecture | Qwen3_5MoeForConditionalGeneration | Qwen2ForCausalLM |
| Context | 256K tokens | 40K tokens |
| Modalities | Vision, Function-calling | Chat, Reasoning, Function-calling |
| License | Apache 2.0 | Apache 2.0 |
| Released | Apr 2026 | Mar 2025 |
Frequently Asked Questions
Which is better, Qwen3.6 35B A3B or QwQ 32B?
Qwen3.6 35B A3B leads llmrun Score 106.8 to 96.2; 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 Qwen3.6 35B A3B for higher llmrun Score and 4.7× faster on RTX 4090; choose QwQ 32B for also does chat, reasoning.
Which needs less VRAM, Qwen3.6 35B A3B or QwQ 32B?
At Q4_K_M, Qwen3.6 35B A3B requires 22.0 GB while QwQ 32B needs 20.5 GB, making QwQ 32B the easier model to run on your local setup.
Which is faster on RTX 4090?
Estimated decode speed on RTX 4090 is about 151 tok/s for Qwen3.6 35B A3B (Q4_K_M) and 32 tok/s for QwQ 32B (Q4_K_M), so Qwen3.6 35B A3B is faster. Estimates, ±20%.
Can I run Qwen3.6 35B A3B or QwQ 32B on a 16 GB GPU?
Qwen3.6 35B A3B fits at Q2_K; QwQ 32B fits at IQ2_M.
Which has a longer context window, Qwen3.6 35B A3B or QwQ 32B?
Qwen3.6 35B A3B supports 262,144 tokens and QwQ 32B supports 40,960 tokens.