Back to leaderboard

gemma-3-4b-it-q4-k-m

OLLAMA GGUF

llama · 4B · Q4_K_M

Excellent

Jul 9, 2026 · Intel Core™ i5-10400

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

LM-STUDIO MLX

qwen3_moe · 30B · MXFP4

Excellent

Apr 22, 2026 · Apple M2 Max

Global Score
80 vs 95
Hardware Fit
100 vs 94
Quality Score
71 vs 96

Hardware

gemma-3-4b-it-q4-k-m qwen3-30b-a3b-thin…
MachineMac ProMac Studio
CPUIntel Core™ i5-10400Apple M2 Max
Cores1212
RAM32 GB96 GB
GPUAMD Radeon RX 6700 XTApple M2 Max
OSmacOS 26.5.1macOS 26.1
Archx64arm64
Power Modebalancedbalanced

Performance

gemma-3-4b-it-q4-k-m qwen3-30b-a3b-thin…
Tokens/sec75.080.4
First chunk136 ms46 ms
TTFT136 ms1.8 s
Load time0.0 sN/A
Memory usage0.8 GB21.2 GB
Memory %3%22%

HW Fit Score Breakdown

gemma-3-4b-it-q4-k-m

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

qwen3-30b-a3b-thinking-…

Speed
50/50
TTFT
14/20
Memory
30/30

Quality

gemma-3-4b-it-q4-k-m

Reasoning
11/20
Coding
17/20
Instruction
14/20
Structured
14/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

qwen3-30b-a3b-thinking-…

Reasoning
19/20
Coding
18/20
Instruction
19/20
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