llama3.2:latest
OLLAMA GGUFllama · 3.2B · Q4_K_M
May 27, 2026 · AMD Ryzen 5 2600X Six-Core Processor
qwen/qwen3.6-35b-a3b
LM-STUDIO MLXqwen3_5_moe · 35B · 4bit
Jul 17, 2026 · Apple M5 Max
Global Score
76 vs 89
Hardware Fit
100 vs 97
Quality Score
65 vs 86
Hardware
llama3.2:latest qwen/qwen3.6-35b-a3b
MachineMicro-Star International Co., Ltd. MS-7B79MacBook Pro
CPUAMD Ryzen 5 2600X Six-Core ProcessorApple M5 Max
Cores1218
RAM16 GB64 GB
GPUNVIDIA GeForce GTX 1080Apple M5 Max
OSMicrosoft Windows 11 Famille 10.0.26200macOS 27.0
Archx64arm64
Power Modebalancedbalanced
Performance
llama3.2:latest qwen/qwen3.6-35b-a3b
Tokens/sec57.0130.2
First chunk264 ms5 ms
TTFT264 ms135 ms
Load time9.7 sN/A
Memory usage2.6 GB26.6 GB
Memory %16%42%
HW Fit Score Breakdown
llama3.2:latest
Speed
50/50
TTFT
20/20
Memory
30/30
qwen/qwen3.6-35b-a3b
Speed
50/50
TTFT
20/20
Memory
27/30
Quality
llama3.2:latest
Reasoning
11/20
Coding
15/20
Instruction
15/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor Multilingual: Strong
qwen/qwen3.6-35b-a3b
Reasoning
15/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Adequate 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