llama3.1:8b-instruct-q4_K_S
OLLAMA GGUFllama · 8.0B · Q4_K_S
Nov 22, 2026 · C1-Pro
qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-mlx
LM-STUDIO MLXqwen3_moe · 30B · MXFP4
Apr 20, 2026 · Apple M2 Max
Global Score
70 vs 97
Hardware Fit
73 vs 95
Quality Score
68 vs 98
Hardware
llama3.1:8b-instru… qwen3-30b-a3b-thin…
Machine—Mac Studio
CPUC1-ProApple M2 Max
Cores012
RAM11 GB96 GB
GPUIntegrated / UnknownApple M2 Max
OSunknown unknownmacOS 26.1
Archarm64arm64
Power Modeunknownbalanced
Performance
llama3.1:8b-instru… qwen3-30b-a3b-thin…
Tokens/sec6.579.6
First chunk950 ms11 ms
TTFT950 ms1.7 s
Load time11.5 s7.1 s
Memory usage4.4 GB0.0 GB
Memory %38%0%
HW Fit Score Breakdown
llama3.1:8b-instruct-q4…
Speed
25/50
TTFT
20/20
Memory
28/30
qwen3-30b-a3b-thinking-…
Speed
50/50
TTFT
15/20
Memory
30/30
Quality
llama3.1:8b-instruct-q4…
Reasoning
11/20
Coding
17/20
Instruction
11/20
Structured
14/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
qwen3-30b-a3b-thinking-…
Reasoning
19/20
Coding
19/20
Instruction
20/20
Structured
15/15
Math
15/15
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