Qwen3.5 4B vs Qwen3.5 9B
Qwen3.5 4B and Qwen3.5 9B match in llmrun Score, with values of 98.5 versus 99.4; both fit 24 GB at Q4_K_M; Qwen3.5 4B is 2.0× faster on RTX 4090 (~201 vs ~103 tok/s).
Model A · Alibaba
Qwen3.5 4B4.7B · 256K context · Apache 2.0 · Feb 2026
Model B · Alibaba
Qwen3.5 9B9.7B · 256K context · Apache 2.0 · Feb 2026
Choose Qwen3.5 4B if you want…
2.0× faster on RTX 4090
~201 vs ~103 tok/s
Lighter on memory
3.3 vs 6.4 GB at Q4_K_M
Choose Qwen3.5 9B if you want…
Ahead on the benchmarks
3 of 3 shared boards
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 4B
Q4_K_M · ~54 tok/s
3.4 GB · up to 128Kfaster
Qwen3.5 9B
Q4_K_M · ~28 tok/s
6.6 GB · up to 32K
12 GB
RTX 3060 12GB · 12 GB tier
Qwen3.5 4B
Q4_K_M · ~72 tok/s
3.4 GB · up to 256Kfaster
Qwen3.5 9B
Q4_K_M · ~37 tok/s
6.6 GB · up to 128K
16 GB
RTX 5060 Ti 16GB · 16 GB tier
Qwen3.5 4B
Q4_K_M · ~89 tok/s
3.4 GB · up to 256Kfaster
Qwen3.5 9B
Q4_K_M · ~46 tok/s
6.6 GB · up to 256K
24 GBreference
RTX 4090 · 24 GB tier
Qwen3.5 4B
Q4_K_M · ~201 tok/s
3.4 GB · up to 256Kfaster
Qwen3.5 9B
Q4_K_M · ~103 tok/s
6.6 GB · up to 256K
32 GB
RTX 5090 · 32 GB tier
Qwen3.5 4B
Q4_K_M · ~357 tok/s
3.4 GB · up to 256Kfaster
Qwen3.5 9B
Q4_K_M · ~183 tok/s
6.6 GB · up to 256K
48 GB
RTX A6000 · 48 GB tier
Qwen3.5 4B
Q4_K_M · ~153 tok/s
3.4 GB · up to 256Kfaster
Qwen3.5 9B
Q4_K_M · ~79 tok/s
6.6 GB · up to 256K
Mac 32 GB
Mac Mini M4 · Macs
Qwen3.5 4B
Q4_K_M · ~26 tok/s
3.4 GB · up to 256Kfaster
Qwen3.5 9B
Q4_K_M · ~13 tok/s
6.6 GB · up to 256K
Mac 64 GB
Mac Studio M4 Max · Macs
Qwen3.5 4B
Q4_K_M · ~117 tok/s
3.4 GB · up to 256Kfaster
Qwen3.5 9B
Q4_K_M · ~60 tok/s
6.6 GB · up to 256K
Mac 128 GB
Mac Studio M4 Max · Macs
Qwen3.5 4B
Q4_K_M · ~117 tok/s
3.4 GB · up to 256Kfaster
Qwen3.5 9B
Q4_K_M · ~60 tok/s
6.6 GB · up to 256K
Reference GPU: RTX 4090. Tinted cell = the better pick on that machine (fits, more headroom, or at least 10% faster).
Overall
Qwen3.5 4B
Qwen3.5 9B
Science
Qwen3.5 4B
no data
Qwen3.5 9B
Reasoning
Qwen3.5 4B
no data
Qwen3.5 9B
Qwen3.5 4B · #64 of 106 open models · #12 of 36 that fit 24 GB
Qwen3.5 9B · #59 of 106 open models · #10 of 36 that fit 24 GB
Qwen3.5 4B
55.8%#43/88 open
IndependentEpoch AI · Feb 2026
Qwen3.5 9B
61.7%#39/88 open
IndependentEpoch AI · Feb 2026
Qwen3.5 4B
79.1%#26/146 open
IndependentTIGER-Lab
Qwen3.5 9B
82.5%#17/146 open
IndependentTIGER-Lab
Qwen3.5 4B
0.0%#81/84 open
Lab-reportedEpoch AI · Feb 2026
Qwen3.5 9B
0.6%#46/84 open
Lab-reportedEpoch AI · Feb 2026
5 more boards (other shared and single-model boards)
Only Qwen3.5 9B (5)
- GPQA Diamond79.0%
- Terminal-Bench9.2%
- SciCode29.5%
- DTBench71.2%
- LMCA24.5%
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 4B
2.5 GB2.2 GB file
32K 3.0 GB · 128K 5.0 GB
Qwen3.5 9B
4.7 GB4.3 GB file
32K 5.5 GB · 128K 8.7 GB
Q3_K_S
Qwen3.5 4B
2.5 GB2.1 GB file
32K 3.0 GB · 128K 5.0 GB
Qwen3.5 9B
4.8 GB4.3 GB file
32K 5.6 GB · 128K 8.8 GB
Q3_K_M
Qwen3.5 4B
2.7 GB2.3 GB file
32K 3.2 GB · 128K 5.3 GB
Qwen3.5 9B
5.3 GB4.7 GB file
32K 6.1 GB · 128K 9.3 GB
Q4_0
Qwen3.5 4B
2.8 GB2.6 GB file
32K 3.3 GB · 128K 5.3 GB
Qwen3.5 9B
5.4 GB5.4 GB file
32K 6.2 GB · 128K 9.4 GB
Q4_K_M
Qwen3.5 4B
3.3 GB2.7 GB file
32K 3.8 GB · 128K 5.8 GB
Qwen3.5 9B
6.4 GB5.7 GB file
32K 7.2 GB · 128K 10.4 GB
Q5_K_M
Qwen3.5 4B
3.8 GB3.1 GB file
32K 4.3 GB · 128K 6.3 GB
Qwen3.5 9B
7.5 GB6.6 GB file
32K 8.3 GB · 128K 11.5 GB
Q6_K
Qwen3.5 4B
4.3 GB3.5 GB file
32K 4.8 GB · 128K 6.8 GB
Qwen3.5 9B
8.5 GB7.5 GB file
32K 9.3 GB · 128K 12.6 GB
Q8_0
Qwen3.5 4B
5.1 GB4.5 GB file
32K 5.6 GB · 128K 7.7 GB
Qwen3.5 9B
10.2 GB9.5 GB file
32K 11.0 GB · 128K 14.3 GB
16 more quants
IQ2_XXS
Qwen3.5 4B
1.8 GB1.5 GB file
32K 2.3 GB · 128K 4.3 GB
Qwen3.5 9B
3.2 GB3.2 GB file
32K 4.0 GB · 128K 7.3 GB
IQ2_S
Qwen3.5 4B
not listed
Qwen3.5 9B
3.6 GB3.5 GB file
32K 4.4 GB · 128K 7.6 GB
IQ2_M
Qwen3.5 4B
2.0 GB1.8 GB file
32K 2.5 GB · 128K 4.6 GB
Qwen3.5 9B
3.8 GB3.6 GB file
32K 4.6 GB · 128K 7.9 GB
IQ3_XXS
Qwen3.5 4B
2.3 GB1.9 GB file
32K 2.8 GB · 128K 4.8 GB
Qwen3.5 9B
4.3 GB4.0 GB file
32K 5.1 GB · 128K 8.3 GB
IQ3_XS
Qwen3.5 4B
2.4 GB2.4 GB file
32K 2.9 GB · 128K 4.9 GB
Qwen3.5 9B
4.6 GB4.8 GB file
32K 5.4 GB · 128K 8.6 GB
IQ3_S
Qwen3.5 4B
not listed
Qwen3.5 9B
4.7 GB3.2 GB file
32K 5.5 GB · 128K 8.7 GB
IQ3_M
Qwen3.5 4B
2.6 GB2.5 GB file
32K 3.1 GB · 128K 5.1 GB
Qwen3.5 9B
4.9 GB5.0 GB file
32K 5.7 GB · 128K 8.9 GB
Q3_K_L
Qwen3.5 4B
2.9 GB2.7 GB file
32K 3.4 GB · 128K 5.4 GB
Qwen3.5 9B
5.5 GB5.4 GB file
32K 6.3 GB · 128K 9.6 GB
IQ4_XS
Qwen3.5 4B
3.0 GB2.5 GB file
32K 3.5 GB · 128K 5.5 GB
Qwen3.5 9B
5.8 GB5.2 GB file
32K 6.6 GB · 128K 9.8 GB
IQ4_NL
Qwen3.5 4B
3.1 GB2.6 GB file
32K 3.6 GB · 128K 5.6 GB
Qwen3.5 9B
6.0 GB5.4 GB file
32K 6.8 GB · 128K 10.0 GB
Q4_1
Qwen3.5 4B
3.1 GB2.8 GB file
32K 3.6 GB · 128K 5.6 GB
Qwen3.5 9B
6.0 GB5.8 GB file
32K 6.8 GB · 128K 10.0 GB
Q4_K_S
Qwen3.5 4B
3.1 GB2.6 GB file
32K 3.6 GB · 128K 5.6 GB
Qwen3.5 9B
6.0 GB5.4 GB file
32K 6.8 GB · 128K 10.0 GB
Q4_K_L
Qwen3.5 4B
3.3 GB3.2 GB file
32K 3.8 GB · 128K 5.8 GB
Qwen3.5 9B
6.5 GB6.9 GB file
32K 7.3 GB · 128K 10.5 GB
Q5_K_S
Qwen3.5 4B
3.7 GB3.0 GB file
32K 4.2 GB · 128K 6.2 GB
Qwen3.5 9B
7.2 GB6.4 GB file
32K 8.0 GB · 128K 11.2 GB
Q5_K_L
Qwen3.5 4B
3.9 GB3.6 GB file
32K 4.4 GB · 128K 6.4 GB
Qwen3.5 9B
7.6 GB7.7 GB file
32K 8.4 GB · 128K 11.6 GB
BF16
Qwen3.5 4B
9.8 GB8.4 GB file
32K 10.3 GB · 128K 12.3 GB
Qwen3.5 9B
19.9 GB17.9 GB file
32K 20.7 GB · 128K 23.9 GB
Qwen3.5 4B
Ollama · Q4_K_M
ollama run hf.co/unsloth/Qwen3.5-4B-GGUF:Q4_K_MQwen3.5 9B
Ollama · Q4_K_M
ollama run hf.co/unsloth/Qwen3.5-9B-GGUF:Q4_K_M| Spec | Qwen3.5 4B | Qwen3.5 9B |
|---|---|---|
| Publisher | Alibaba | Alibaba |
| Parameters | 4.7B | 9.7B |
| Architecture | Qwen3_5ForConditionalGeneration | Qwen3_5ForConditionalGeneration |
| Context | 256K tokens | 256K tokens |
| Modalities | Vision, Function-calling | Vision, Function-calling |
| License | Apache 2.0 | Apache 2.0 |
| Released | Feb 2026 | Feb 2026 |
Frequently Asked Questions
Which is better, Qwen3.5 4B or Qwen3.5 9B?
Qwen3.5 4B and Qwen3.5 9B match in llmrun Score, with values of 98.5 versus 99.4; both fit 24 GB at Q4_K_M; Qwen3.5 4B is 2.0× faster on RTX 4090 (~201 vs ~103 tok/s). Choose Qwen3.5 4B for 2.0× faster on RTX 4090 and lighter on memory; choose Qwen3.5 9B for ahead on the benchmarks.
Which needs less VRAM, Qwen3.5 4B or Qwen3.5 9B?
At Q4_K_M, Qwen3.5 4B requires 3.3 GB while Qwen3.5 9B needs 6.4 GB, making Qwen3.5 4B the easier model to run on your local setup.
Which is faster on RTX 4090?
Estimated decode speed on RTX 4090 is about 201 tok/s for Qwen3.5 4B (Q4_K_M) and 103 tok/s for Qwen3.5 9B (Q4_K_M), so Qwen3.5 4B is faster. Estimates, ±20%.
Can I run Qwen3.5 4B or Qwen3.5 9B on a 16 GB GPU?
Qwen3.5 4B fits at Q4_K_M; Qwen3.5 9B fits at Q4_K_M.
Which has a longer context window, Qwen3.5 4B or Qwen3.5 9B?
Qwen3.5 4B supports 262,144 tokens and Qwen3.5 9B supports 262,144 tokens.