Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Mar 5, 2026 · Intel Core™ i5-6500

qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-mlx

LM-STUDIO MLX

qwen3_moe · 30B · MXFP4

Excellent

Apr 20, 2026 · Apple M2 Max

Global Score
61 vs 97
Hardware Fit
69 vs 95
Quality Score
58 vs 98

Hardware

qwen3.5:4b qwen3-30b-a3b-thin…
MachineGigabyte Technology Co., Ltd. H170M-D3HMac Studio
CPUIntel Core™ i5-6500Apple M2 Max
Cores412
RAM16 GB96 GB
GPUGP104 [GeForce GTX 1070]Apple M2 Max
OSUbuntu 24.04.4 LTSmacOS 26.1
Archx64arm64
Power Modelow-powerbalanced

Performance

qwen3.5:4b qwen3-30b-a3b-thin…
Tokens/sec35.779.6
First chunk438 ms11 ms
TTFT5.1 s1.7 s
Load time40.1 s7.1 s
Memory usage5.5 GB0.0 GB
Memory %35%0%

HW Fit Score Breakdown

qwen3.5:4b

Speed
50/50
TTFT
11/20
Memory
8/30

qwen3-30b-a3b-thinking-…

Speed
50/50
TTFT
15/20
Memory
30/30

Quality

qwen3.5:4b

Reasoning
18/20
Coding
1/20
Instruction
8/20
Structured
8/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Weak Structured Output: Adequate Math: Strong Multilingual: Strong

qwen3-30b-a3b-thinking-…

Reasoning
19/20
Coding
19/20
Instruction
20/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest