Qwen3.5 4B vs Qwen3 8B

Qwen3.5 4B leads llmrun Score 98.5 to 93.9 (ranges overlap); both fit 24 GB at Q4_K_M; Qwen3.5 4B is 1.7× faster on RTX 4090 (~201 vs ~119 tok/s).

Model A · Alibaba

Qwen3.5 4B

98.5llmrun Score

4.7B · 256K context · Apache 2.0 · Feb 2026

VisionFunctions

Model B · Alibaba

Qwen3 8B

93.9llmrun Score

8.2B · 40K context · Apache 2.0 · Apr 2025

ChatFunctions

Which should you choose?

Choose Qwen3.5 4B if you want…

Higher llmrun Score
98.5 vs 93.9, ranges overlap
1.7× faster on RTX 4090
~201 vs ~119 tok/s
Lighter on memory
3.3 vs 5.5 GB at Q4_K_M
Longer context window
256K vs 40K tokens
Also does vision
Qwen3 8B doesn't list it
Newer release
Feb 2026 vs Apr 2025

Choose Qwen3 8B if you want…

Also does chat
Qwen3.5 4B doesn't list it

On your hardware

Each model at its default quant (Q4_K_M), a smaller one when it must. Estimates, ±20%.

MemoryQwen3.5 4BQwen3 8B

8 GB

RTX 4060 · 8 GB tier

Qwen3.5 4B

Q4_K_M · ~54 tok/s

3.4 GB · up to 128Kfaster

Qwen3 8B

Q4_K_M · ~32 tok/s

7.6 GB · up to 16K

12 GB

RTX 3060 12GB · 12 GB tier

Qwen3.5 4B

Q4_K_M · ~72 tok/s

3.4 GB · up to 256Kfaster

Qwen3 8B

Q4_K_M · ~42 tok/s

7.6 GB · up to 40K

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 8B

Q4_K_M · ~53 tok/s

7.6 GB · up to 40K

24 GBreference

RTX 4090 · 24 GB tier

Qwen3.5 4B

Q4_K_M · ~201 tok/s

3.4 GB · up to 256Kfaster

Qwen3 8B

Q4_K_M · ~119 tok/s

7.6 GB · up to 40K

32 GB

RTX 5090 · 32 GB tier

Qwen3.5 4B

Q4_K_M · ~357 tok/s

3.4 GB · up to 256Kfaster

Qwen3 8B

Q4_K_M · ~211 tok/s

7.6 GB · up to 40K

48 GB

RTX A6000 · 48 GB tier

Qwen3.5 4B

Q4_K_M · ~153 tok/s

3.4 GB · up to 256Kfaster

Qwen3 8B

Q4_K_M · ~90 tok/s

7.6 GB · up to 40K

Mac 32 GB

Mac Mini M4 · Macs

Qwen3.5 4B

Q4_K_M · ~26 tok/s

3.4 GB · up to 256Kfaster

Qwen3 8B

Q4_K_M · ~15 tok/s

7.6 GB · up to 40K

Mac 64 GB

Mac Studio M4 Max · Macs

Qwen3.5 4B

Q4_K_M · ~117 tok/s

3.4 GB · up to 256Kfaster

Qwen3 8B

Q4_K_M · ~69 tok/s

7.6 GB · up to 40K

Mac 128 GB

Mac Studio M4 Max · Macs

Qwen3.5 4B

Q4_K_M · ~117 tok/s

3.4 GB · up to 256Kfaster

Qwen3 8B

Q4_K_M · ~69 tok/s

7.6 GB · up to 40K

Reference GPU: RTX 4090. Tinted cell = the better pick on that machine (fits, more headroom, or at least 10% faster).

llmrun Score

with its 90% range · bars share one scale

Qwen3.5 4B Qwen3 8B

Overall

Qwen3.5 4B

98.594–103

Qwen3 8B

93.991–97

Science

Qwen3.5 4B

no data

Qwen3 8B

87.780–95

Reasoning

Qwen3.5 4B

no data

Qwen3 8B

81.471–91

Qwen3.5 4B · #64 of 106 open models · #12 of 36 that fit 24 GB

Qwen3 8B · #73 of 106 open models · #19 of 36 that fit 24 GB

Benchmarks

2 shared boards: Qwen3.5 4B leads 0, Qwen3 8B leads 0 · Benchmarks imported Nov 2026

BoardQwen3.5 4BQwen3 8B

AIME 2024/2025

Qwen3.5 4B

55.8%#43/88 open

IndependentEpoch AI · Feb 2026

Qwen3 8B

56.1%#42/88 open

IndependentEpoch AI · Apr 2025

CritPt

Qwen3.5 4B

0.0%#81/84 open

Lab-reportedEpoch AI · Feb 2026

Qwen3 8B

0.0%#82/84 open

Lab-reportedEpoch AI · Apr 2025

6 more boards (other shared and single-model boards)

Only Qwen3.5 4B (1)

MMLU-Pro79.1%

Only Qwen3 8B (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.

QuantQwen3.5 4BQwen3 8B

Q2_K

Qwen3.5 4B

2.5 GB2.2 GB file

32K 3.0 GB · 128K 5.0 GB

Qwen3 8B

4.1 GB3.3 GB file

32K 8.6 GB · 128K —

Q3_K_S

Qwen3.5 4B

2.5 GB2.1 GB file

32K 3.0 GB · 128K 5.0 GB

Qwen3 8B

4.2 GB3.8 GB file

32K 8.7 GB · 128K —

Q3_K_M

Qwen3.5 4B

2.7 GB2.3 GB file

32K 3.2 GB · 128K 5.3 GB

Qwen3 8B

4.6 GB4.1 GB file

32K 9.1 GB · 128K —

Q4_0

Qwen3.5 4B

2.8 GB2.6 GB file

32K 3.3 GB · 128K 5.3 GB

Qwen3 8B

4.7 GB4.8 GB file

32K 9.2 GB · 128K —

Q4_K_M

Qwen3.5 4B

3.3 GB2.7 GB file

32K 3.8 GB · 128K 5.8 GB

Qwen3 8B

5.5 GB5.0 GB file

32K 10.1 GB · 128K —

Q5_K_M

Qwen3.5 4B

3.8 GB3.1 GB file

32K 4.3 GB · 128K 6.3 GB

Qwen3 8B

6.4 GB5.9 GB file

32K 11.0 GB · 128K —

Q6_K

Qwen3.5 4B

4.3 GB3.5 GB file

32K 4.8 GB · 128K 6.8 GB

Qwen3 8B

7.4 GB6.7 GB file

32K 11.9 GB · 128K —

Q8_0

Qwen3.5 4B

5.1 GB4.5 GB file

32K 5.6 GB · 128K 7.7 GB

Qwen3 8B

8.8 GB8.7 GB file

32K 13.3 GB · 128K —

19 more quants

IQ2_XXS

Qwen3.5 4B

1.8 GB1.5 GB file

32K 2.3 GB · 128K 4.3 GB

Qwen3 8B

2.9 GB2.6 GB file

32K 7.4 GB · 128K —

IQ2_XS

Qwen3.5 4B

not listed

Qwen3 8B

3.1 GB2.7 GB file

32K 7.6 GB · 128K —

IQ2_S

Qwen3.5 4B

not listed

Qwen3 8B

3.2 GB2.9 GB file

32K 7.7 GB · 128K —

IQ2_M

Qwen3.5 4B

2.0 GB1.8 GB file

32K 2.5 GB · 128K 4.6 GB

Qwen3 8B

3.4 GB3.1 GB file

32K 7.9 GB · 128K —

IQ3_XXS

Qwen3.5 4B

2.3 GB1.9 GB file

32K 2.8 GB · 128K 4.8 GB

Qwen3 8B

3.8 GB3.4 GB file

32K 8.3 GB · 128K —

Q2_K_S

Qwen3.5 4B

not listed

Qwen3 8B

3.9 GB3.1 GB file

32K 8.4 GB · 128K —

IQ3_XS

Qwen3.5 4B

2.4 GB2.4 GB file

32K 2.9 GB · 128K 4.9 GB

Qwen3 8B

4.0 GB3.6 GB file

32K 8.5 GB · 128K —

IQ3_S

Qwen3.5 4B

not listed

Qwen3 8B

4.1 GB3.5 GB file

32K 8.6 GB · 128K —

IQ3_M

Qwen3.5 4B

2.6 GB2.5 GB file

32K 3.1 GB · 128K 5.1 GB

Qwen3 8B

4.3 GB3.9 GB file

32K 8.8 GB · 128K —

Q3_K_L

Qwen3.5 4B

2.9 GB2.7 GB file

32K 3.4 GB · 128K 5.4 GB

Qwen3 8B

4.8 GB4.4 GB file

32K 9.3 GB · 128K —

IQ4_XS

Qwen3.5 4B

3.0 GB2.5 GB file

32K 3.5 GB · 128K 5.5 GB

Qwen3 8B

5.0 GB4.6 GB file

32K 9.5 GB · 128K —

IQ4_NL

Qwen3.5 4B

3.1 GB2.6 GB file

32K 3.6 GB · 128K 5.6 GB

Qwen3 8B

5.2 GB4.8 GB file

32K 9.7 GB · 128K —

Q4_1

Qwen3.5 4B

3.1 GB2.8 GB file

32K 3.6 GB · 128K 5.6 GB

Qwen3 8B

5.2 GB5.2 GB file

32K 9.7 GB · 128K —

Q4_K_S

Qwen3.5 4B

3.1 GB2.6 GB file

32K 3.6 GB · 128K 5.6 GB

Qwen3 8B

5.2 GB4.8 GB file

32K 9.7 GB · 128K —

Q4_K_L

Qwen3.5 4B

3.3 GB3.2 GB file

32K 3.8 GB · 128K 5.8 GB

Qwen3 8B

5.6 GB5.5 GB file

32K 10.2 GB · 128K —

Q5_0

Qwen3.5 4B

not listed

Qwen3 8B

5.7 GB5.7 GB file

32K 10.3 GB · 128K —

Q5_K_S

Qwen3.5 4B

3.7 GB3.0 GB file

32K 4.2 GB · 128K 6.2 GB

Qwen3 8B

6.2 GB5.7 GB file

32K 10.8 GB · 128K —

Q5_K_L

Qwen3.5 4B

3.9 GB3.6 GB file

32K 4.4 GB · 128K 6.4 GB

Qwen3 8B

6.5 GB6.2 GB file

32K 11.1 GB · 128K —

BF16

Qwen3.5 4B

9.8 GB8.4 GB file

32K 10.3 GB · 128K 12.3 GB

Qwen3 8B

17.0 GB16.4 GB file

32K 21.5 GB · 128K —

How to run each

Qwen3.5 4B

Ollama · Q4_K_M

$ollama run hf.co/unsloth/Qwen3.5-4B-GGUF:Q4_K_M

All ways to run Qwen3.5 4B →

Qwen3 8B

Ollama · Q4_K_M

$ollama run hf.co/Qwen/Qwen3-8B-GGUF:Q4_K_M

All ways to run Qwen3 8B →

Specifications

Specifications of Qwen3.5 4B and Qwen3 8B
Spec	Qwen3.5 4B	Qwen3 8B
Publisher	Alibaba	Alibaba
Parameters	4.7B	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 4B or Qwen3 8B?

Qwen3.5 4B leads llmrun Score 98.5 to 93.9 (ranges overlap); both fit 24 GB at Q4_K_M; Qwen3.5 4B is 1.7× faster on RTX 4090 (~201 vs ~119 tok/s). Choose Qwen3.5 4B for higher llmrun Score and 1.7× faster on RTX 4090; choose Qwen3 8B for also does chat.

Which needs less VRAM, Qwen3.5 4B or Qwen3 8B?

At Q4_K_M, Qwen3.5 4B requires 3.3 GB while Qwen3 8B needs 5.5 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 119 tok/s for Qwen3 8B (Q4_K_M), so Qwen3.5 4B is faster. Estimates, ±20%.

Can I run Qwen3.5 4B or Qwen3 8B on a 16 GB GPU?

Qwen3.5 4B fits at Q4_K_M; Qwen3 8B fits at Q4_K_M.

Which has a longer context window, Qwen3.5 4B or Qwen3 8B?

Qwen3.5 4B supports 262,144 tokens and Qwen3 8B supports 40,960 tokens.