Back to leaderboard

gemma4:12b-fast

OLLAMA GGUF

gemma4 · 11.9B · Q4_K_M

Not Rec.

Nov 13, 2026 · Intel Gen Intel® Core™ i7-12700

qwen/qwen3-8b

LM-STUDIO MLX

qwen3 · 8B · 4bit

Excellent

Mar 5, 2026 · Apple M4 Pro

Global Score
85 vs 89
Hardware Fit
80 vs 95
Quality Score
87 vs 87

Hardware

gemma4:12b-fast qwen/qwen3-8b
MachineASUSMac mini
CPUIntel Gen Intel® Core™ i7-12700Apple M4 Pro
Cores2014
RAM30 GB64 GB
GPUAlder Lake-S GT1 [UHD Graphics 770], NVIDIA GeForce RTX 3060Apple M4 Pro
OSUbuntu 26.04.1 LTSmacOS 15.7.4
Archx64arm64
Power Modelow-powerbalanced

Performance

gemma4:12b-fast qwen/qwen3-8b
Tokens/sec75.933.4
First chunk169 ms257 ms
TTFT30.0 s257 ms
Load time8.4 sN/A
Memory usage1.3 GB4.3 GB
Memory %5%7%

HW Fit Score Breakdown

gemma4:12b-fast

Speed
50/50
TTFT
0/20
Memory
30/30

qwen/qwen3-8b

Speed
45/50
TTFT
20/20
Memory
30/30

Quality

gemma4:12b-fast

Reasoning
18/20
Coding
14/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen/qwen3-8b

Reasoning
19/20
Coding
14/20
Instruction
16/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View gemma4:12b-fast details | View qwen/qwen3-8b 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