gemma-3-27b-it-qat
LM-STUDIO MLXgemma3 · 27B · 4bit
Mar 5, 2026 · Apple M4 Pro
codestral:latest
OLLAMA GGUFllama · 22.2B · Q4_0
Sep 15, 2026 · Intel Core™ i5-14400F
Global Score
76 vs 76
Hardware Fit
51 vs 91
Quality Score
87 vs 69
Hardware
gemma-3-27b-it-qat codestral:latest
MachineMac miniGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4
CPUApple M4 ProIntel Core™ i5-14400F
Cores1416
RAM64 GB32 GB
GPUApple M4 ProNVIDIA GeForce RTX 5060 Ti
OSmacOS 15.7.4Microsoft Windows 11 Professionnel 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
gemma-3-27b-it-qat codestral:latest
Tokens/sec8.927.4
First chunk3976 ms86 ms
TTFT4.0 s86 ms
Load timeN/A7.2 s
Memory usage15.7 GB12.6 GB
Memory %25%40%
HW Fit Score Breakdown
gemma-3-27b-it-qat
Speed
12/50
TTFT
9/20
Memory
30/30
codestral:latest
Speed
43/50
TTFT
20/20
Memory
28/30
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
codestral:latest
Reasoning
11/20
Coding
17/20
Instruction
11/20
Structured
13/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest