Back to leaderboard

qwen3:4b

OLLAMA GGUF

qwen3 · 4.0B · Q4_K_M

Not Rec.

Nov 4, 2026 · Intel Core™ i7-9700

qwen/qwen3.6-35b-a3b

LM-STUDIO MLX

qwen3_5_moe · 35B · 6bit

Excellent

Jul 17, 2026 · Apple M5 Max

Global Score
29 vs 87
Hardware Fit
84 vs 90
Quality Score
6 vs 86

Hardware

qwen3:4b qwen/qwen3.6-35b-a3b
MachineVMware, Inc. VMware Virtual PlatformMacBook Pro
CPUIntel Core™ i7-9700Apple M5 Max
Cores418
RAM16 GB64 GB
GPUIntegrated / UnknownApple M5 Max
OSUbuntu 24.04.5 LTSmacOS 27.0
Archx64arm64
Power Modeunknownbalanced

Performance

qwen3:4b qwen/qwen3.6-35b-a3b
Tokens/sec10.486.5
First chunk857 ms9 ms
TTFT857 ms175 ms
Load time41.0 sN/A
Memory usage3.0 GB37.9 GB
Memory %19%59%

HW Fit Score Breakdown

qwen3:4b

Speed
34/50
TTFT
20/20
Memory
30/30

qwen/qwen3.6-35b-a3b

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

Quality

qwen3:4b

Reasoning
0/20
Coding
2/20
Instruction
2/20
Structured
0/15
Math
1/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

qwen/qwen3.6-35b-a3b

Reasoning
16/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3:4b details | View qwen/qwen3.6-35b-a3b details

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