Qwen3.5 9B vs Qwen3 8B
Qwen3.5 9B leads llmrun Score 99.4 to 93.8 (ranges overlap); both fit 24 GB at Q4_K_M.
Model A · Alibaba
Qwen3.5 9B9.7B · 256K context · Apache 2.0 · Feb 2026
Choose Qwen3.5 9B if you want…
Higher llmrun Score
99.4 vs 93.8, ranges overlap
Stronger at science
104.2 vs 87.7
Stronger at reasoning
97.1 vs 81.1
Ahead on the benchmarks
7 of 7 shared boards
Longer context window
256K vs 40K tokens
Also does vision
Qwen3 8B doesn't list it
Choose Qwen3 8B if you want…
Also does chat
Qwen3.5 9B 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
Qwen3.5 9B
Q4_K_M · ~28 tok/s
6.6 GB · up to 32K
Qwen3 8B
Q4_K_M · ~32 tok/s
7.6 GB · up to 16Kfaster
12 GB
RTX 3060 12GB · 12 GB tier
Qwen3.5 9B
Q4_K_M · ~37 tok/s
6.6 GB · up to 128K
Qwen3 8B
Q4_K_M · ~42 tok/s
7.6 GB · up to 40Kfaster
16 GB
RTX 5060 Ti 16GB · 16 GB tier
Qwen3.5 9B
Q4_K_M · ~46 tok/s
6.6 GB · up to 256K
Qwen3 8B
Q4_K_M · ~53 tok/s
7.6 GB · up to 40Kfaster
24 GBreference
RTX 4090 · 24 GB tier
Qwen3.5 9B
Q4_K_M · ~103 tok/s
6.6 GB · up to 256K
Qwen3 8B
Q4_K_M · ~119 tok/s
7.6 GB · up to 40Kfaster
32 GB
RTX 5090 · 32 GB tier
Qwen3.5 9B
Q4_K_M · ~183 tok/s
6.6 GB · up to 256K
Qwen3 8B
Q4_K_M · ~211 tok/s
7.6 GB · up to 40Kfaster
48 GB
RTX A6000 · 48 GB tier
Qwen3.5 9B
Q4_K_M · ~79 tok/s
6.6 GB · up to 256K
Qwen3 8B
Q4_K_M · ~90 tok/s
7.6 GB · up to 40Kfaster
Mac 32 GB
Mac Mini M4 · Macs
Qwen3.5 9B
Q4_K_M · ~13 tok/s
6.6 GB · up to 256K
Qwen3 8B
Q4_K_M · ~15 tok/s
7.6 GB · up to 40Kfaster
Mac 64 GB
Mac Studio M4 Max · Macs
Qwen3.5 9B
Q4_K_M · ~60 tok/s
6.6 GB · up to 256K
Qwen3 8B
Q4_K_M · ~69 tok/s
7.6 GB · up to 40Kfaster
Mac 128 GB
Mac Studio M4 Max · Macs
Qwen3.5 9B
Q4_K_M · ~60 tok/s
6.6 GB · up to 256K
Qwen3 8B
Q4_K_M · ~69 tok/s
7.6 GB · up to 40Kfaster
Reference GPU: RTX 4090. Tinted cell = the better pick on that machine (fits, more headroom, or at least 10% faster).
Overall
Qwen3.5 9B
Qwen3 8B
Science
Qwen3.5 9B
Qwen3 8B
Reasoning
Qwen3.5 9B
Qwen3 8B
Qwen3.5 9B · #49 of 92 open models · #10 of 34 that fit 24 GB
Qwen3 8B · #62 of 92 open models · #18 of 34 that fit 24 GB
Qwen3.5 9B
79.0%#25/97 open
IndependentEpoch AI · Feb 2026
Qwen3 8B
56.8%#43/97 open
IndependentEpoch AI · Apr 2025
Qwen3.5 9B
61.7%#36/85 open
IndependentEpoch AI · Feb 2026
Qwen3 8B
56.1%#39/85 open
IndependentEpoch AI · Apr 2025
Qwen3.5 9B
27.6%#54/65 open
Lab-reportedEpoch AI · Feb 2026
Qwen3 8B
22.6%#60/65 open
Lab-reportedEpoch AI · Apr 2025
Qwen3.5 9B
12.0%#23/67 open
IndependentEpoch AI · Feb 2026
Qwen3 8B
5.0%#31/67 open
IndependentEpoch AI · Apr 2025
Qwen3.5 9B
0.3%#43/65 open
Lab-reportedEpoch AI · Feb 2026
Qwen3 8B
0.0%#63/65 open
Lab-reportedEpoch AI · Apr 2025
Qwen3.5 9B
71.2%#31/68 open
Lab-reportedEpoch AI · Feb 2026
Qwen3 8B
59.7%#50/68 open
Lab-reportedEpoch AI · Apr 2025
Qwen3.5 9B
24.5%#28/54 open
Lab-reportedEpoch AI · Feb 2026
Qwen3 8B
8.8%#49/54 open
Lab-reportedEpoch AI · Apr 2025
3 more boards (other shared and single-model boards)
Only Qwen3.5 9B (2)
- Terminal-Bench9.2%
- MMLU-Pro82.5%
Only Qwen3 8B (1)
- Fiction.LiveBench62.1%
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
Qwen3.5 9B
4.7 GB4.3 GB file
32K 5.5 GB · 128K 8.7 GB
Qwen3 8B
4.1 GB3.3 GB file
32K 8.6 GB · 128K —
Q3_K_S
Qwen3.5 9B
4.8 GB4.3 GB file
32K 5.6 GB · 128K 8.8 GB
Qwen3 8B
4.2 GB3.8 GB file
32K 8.7 GB · 128K —
Q3_K_M
Qwen3.5 9B
5.3 GB4.7 GB file
32K 6.1 GB · 128K 9.3 GB
Qwen3 8B
4.6 GB4.1 GB file
32K 9.1 GB · 128K —
Q4_0
Qwen3.5 9B
5.4 GB5.4 GB file
32K 6.2 GB · 128K 9.4 GB
Qwen3 8B
4.7 GB4.8 GB file
32K 9.2 GB · 128K —
Q4_K_M
Qwen3.5 9B
6.4 GB5.7 GB file
32K 7.2 GB · 128K 10.4 GB
Qwen3 8B
5.5 GB5.0 GB file
32K 10.1 GB · 128K —
Q5_K_M
Qwen3.5 9B
7.5 GB6.6 GB file
32K 8.3 GB · 128K 11.5 GB
Qwen3 8B
6.4 GB5.9 GB file
32K 11.0 GB · 128K —
Q6_K
Qwen3.5 9B
8.5 GB7.5 GB file
32K 9.3 GB · 128K 12.6 GB
Qwen3 8B
7.4 GB6.7 GB file
32K 11.9 GB · 128K —
Q8_0
Qwen3.5 9B
10.2 GB9.5 GB file
32K 11.0 GB · 128K 14.3 GB
Qwen3 8B
8.8 GB8.7 GB file
32K 13.3 GB · 128K —
19 more quants
IQ2_XXS
Qwen3.5 9B
3.2 GB3.2 GB file
32K 4.0 GB · 128K 7.3 GB
Qwen3 8B
2.9 GB2.6 GB file
32K 7.4 GB · 128K —
IQ2_XS
Qwen3.5 9B
not listed
Qwen3 8B
3.1 GB2.7 GB file
32K 7.6 GB · 128K —
IQ2_S
Qwen3.5 9B
3.6 GB3.5 GB file
32K 4.4 GB · 128K 7.6 GB
Qwen3 8B
3.2 GB2.9 GB file
32K 7.7 GB · 128K —
IQ2_M
Qwen3.5 9B
3.8 GB3.6 GB file
32K 4.6 GB · 128K 7.9 GB
Qwen3 8B
3.4 GB3.1 GB file
32K 7.9 GB · 128K —
IQ3_XXS
Qwen3.5 9B
4.3 GB4.0 GB file
32K 5.1 GB · 128K 8.3 GB
Qwen3 8B
3.8 GB3.4 GB file
32K 8.3 GB · 128K —
Q2_K_S
Qwen3.5 9B
not listed
Qwen3 8B
3.9 GB3.1 GB file
32K 8.4 GB · 128K —
IQ3_XS
Qwen3.5 9B
4.6 GB4.8 GB file
32K 5.4 GB · 128K 8.6 GB
Qwen3 8B
4.0 GB3.6 GB file
32K 8.5 GB · 128K —
IQ3_S
Qwen3.5 9B
4.7 GB3.2 GB file
32K 5.5 GB · 128K 8.7 GB
Qwen3 8B
4.1 GB3.8 GB file
32K 8.6 GB · 128K —
IQ3_M
Qwen3.5 9B
4.9 GB5.0 GB file
32K 5.7 GB · 128K 8.9 GB
Qwen3 8B
4.3 GB3.9 GB file
32K 8.8 GB · 128K —
Q3_K_L
Qwen3.5 9B
5.5 GB5.4 GB file
32K 6.3 GB · 128K 9.6 GB
Qwen3 8B
4.8 GB4.4 GB file
32K 9.3 GB · 128K —
IQ4_XS
Qwen3.5 9B
5.8 GB5.2 GB file
32K 6.6 GB · 128K 9.8 GB
Qwen3 8B
5.0 GB4.6 GB file
32K 9.5 GB · 128K —
IQ4_NL
Qwen3.5 9B
6.0 GB5.4 GB file
32K 6.8 GB · 128K 10.0 GB
Qwen3 8B
5.2 GB4.8 GB file
32K 9.7 GB · 128K —
Q4_1
Qwen3.5 9B
6.0 GB5.8 GB file
32K 6.8 GB · 128K 10.0 GB
Qwen3 8B
5.2 GB5.2 GB file
32K 9.7 GB · 128K —
Q4_K_S
Qwen3.5 9B
6.0 GB5.4 GB file
32K 6.8 GB · 128K 10.0 GB
Qwen3 8B
5.2 GB4.8 GB file
32K 9.7 GB · 128K —
Q4_K_L
Qwen3.5 9B
6.5 GB6.9 GB file
32K 7.3 GB · 128K 10.5 GB
Qwen3 8B
5.6 GB5.5 GB file
32K 10.2 GB · 128K —
Q5_0
Qwen3.5 9B
not listed
Qwen3 8B
5.7 GB5.7 GB file
32K 10.3 GB · 128K —
Q5_K_S
Qwen3.5 9B
7.2 GB6.4 GB file
32K 8.0 GB · 128K 11.2 GB
Qwen3 8B
6.2 GB5.7 GB file
32K 10.8 GB · 128K —
Q5_K_L
Qwen3.5 9B
7.6 GB7.7 GB file
32K 8.4 GB · 128K 11.6 GB
Qwen3 8B
6.5 GB6.2 GB file
32K 11.1 GB · 128K —
BF16
Qwen3.5 9B
19.9 GB17.9 GB file
32K 20.7 GB · 128K 23.9 GB
Qwen3 8B
17.0 GB16.4 GB file
32K 21.5 GB · 128K —
Qwen3.5 9B
Ollama · Q4_K_M
ollama run hf.co/unsloth/Qwen3.5-9B-GGUF:Q4_K_MQwen3 8B
Ollama · Q4_K_M
ollama run hf.co/Qwen/Qwen3-8B-GGUF:Q4_K_M| Spec | Qwen3.5 9B | Qwen3 8B |
|---|---|---|
| Publisher | Alibaba | Alibaba |
| Parameters | 9.7B | 8.2B |
| Architecture | Qwen3_5ForConditionalGeneration | Qwen3ForCausalLM |
| Context | 256K tokens | 40K tokens |
| Modalities | Vision, Function-calling | Chat, Function-calling |
| License | Apache 2.0 | Apache 2.0 |
| Released | Feb 2026 | Apr 2025 |
Frequently Asked Questions
Which is better, Qwen3.5 9B or Qwen3 8B?
Qwen3.5 9B leads llmrun Score 99.4 to 93.8 (ranges overlap); both fit 24 GB at Q4_K_M. Choose Qwen3.5 9B for higher llmrun Score and stronger at science; choose Qwen3 8B for also does chat.
Which needs less VRAM, Qwen3.5 9B or Qwen3 8B?
At Q4_K_M, Qwen3.5 9B requires 6.4 GB while Qwen3 8B needs 5.5 GB, making Qwen3 8B the easier model to run on your local setup.
Which is faster on RTX 4090?
Estimated decode speed on RTX 4090 is about 103 tok/s for Qwen3.5 9B (Q4_K_M) and 119 tok/s for Qwen3 8B (Q4_K_M), so Qwen3 8B is faster. Estimates, ±20%.
Can I run Qwen3.5 9B or Qwen3 8B on a 16 GB GPU?
Qwen3.5 9B fits at Q4_K_M; Qwen3 8B fits at Q4_K_M.
Which has a longer context window, Qwen3.5 9B or Qwen3 8B?
Qwen3.5 9B supports 262,144 tokens and Qwen3 8B supports 40,960 tokens.