Back to leaderboard

gemma-3-27b-it-qat

LM-STUDIO MLX

gemma3 · 27B · 4bit

Good

Mar 5, 2026 · Apple M4 Pro

qwen2.5-coder:32b

OLLAMA GGUF

qwen2 · 32.8B · Q4_K_M

Good

Jun 26, 2026 · Cortex-X925

Global Score
76 vs 78
Hardware Fit
51 vs 59
Quality Score
87 vs 86

Hardware

gemma-3-27b-it-qat qwen2.5-coder:32b
MachineMac miniNVIDIA NVIDIA_DGX_Spark
CPUApple M4 ProCortex-X925
Cores1420
RAM64 GB122 GB
GPUApple M4 ProDevice 2e12
OSmacOS 15.7.4Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance

Performance

gemma-3-27b-it-qat qwen2.5-coder:32b
Tokens/sec8.99.5
First chunk3976 ms394 ms
TTFT4.0 s395 ms
Load timeN/A72.1 s
Memory usage15.7 GB26.5 GB
Memory %25%22%

HW Fit Score Breakdown

gemma-3-27b-it-qat

Speed
12/50
TTFT
9/20
Memory
30/30

qwen2.5-coder:32b

Speed
9/50
TTFT
20/20
Memory
30/30

Quality

gemma-3-27b-it-qat

Reasoning
16/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

qwen2.5-coder:32b

Reasoning
14/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View gemma-3-27b-it-qat details | View qwen2.5-coder:32b 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