gemma-3-4b-it-q4-k-m
OLLAMA GGUFllama · 4B · Q4_K_M
Jul 9, 2026 · Intel Core™ i5-10400
qwen/qwen3.6-35b-a3b
LM-STUDIO MLXqwen3_5_moe · 35B · 6bit
Jul 17, 2026 · Apple M5 Max
Global Score
80 vs 87
Hardware Fit
100 vs 90
Quality Score
71 vs 86
Hardware
gemma-3-4b-it-q4-k-m qwen/qwen3.6-35b-a3b
MachineMac ProMacBook Pro
CPUIntel Core™ i5-10400Apple M5 Max
Cores1218
RAM32 GB64 GB
GPUAMD Radeon RX 6700 XTApple M5 Max
OSmacOS 26.5.1macOS 27.0
Archx64arm64
Power Modebalancedbalanced
Performance
gemma-3-4b-it-q4-k-m qwen/qwen3.6-35b-a3b
Tokens/sec75.086.5
First chunk136 ms9 ms
TTFT136 ms175 ms
Load time0.0 sN/A
Memory usage0.8 GB37.9 GB
Memory %3%59%
HW Fit Score Breakdown
gemma-3-4b-it-q4-k-m
Speed
50/50
TTFT
20/20
Memory
30/30
qwen/qwen3.6-35b-a3b
Speed
50/50
TTFT
20/20
Memory
20/30
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
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
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