qwen3.8:27b
OLLAMA GGUFqwen35 · 27.3B · Q4_K_M
Aug 15, 2026 · Cortex-X925
rnj-1:8b
OLLAMA GGUFgemma3 · 8.3B · Q4_K_M
Aug 24, 2026 · Apple M1 Pro
Global Score
85 vs 80
Hardware Fit
79 vs 93
Quality Score
87 vs 74
Hardware
qwen3.8:27b rnj-1:8b
MachineASUSTeK COMPUTER INC. GX10MacBook Pro
CPUCortex-X925Apple M1 Pro
Cores2010
RAM122 GB16 GB
GPUDevice 2e12Apple M1 Pro
OSUbuntu 24.04.4 LTSmacOS 26.6.2
Archarm64arm64
Power Modeperformancebalanced
Performance
qwen3.8:27b rnj-1:8b
Tokens/sec27.422.3
First chunk593 ms404 ms
TTFT593 ms404 ms
Load time0.3 s3.7 s
Memory usage18.2 GB8.3 GB
Memory %15%52%
HW Fit Score Breakdown
qwen3.8:27b
Speed
29/50
TTFT
20/20
Memory
30/30
rnj-1:8b
Speed
49/50
TTFT
20/20
Memory
24/30
Quality
qwen3.8:27b
Reasoning
18/20
Coding
17/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
rnj-1:8b
Reasoning
12/20
Coding
19/20
Instruction
15/20
Structured
5/15
Math
14/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Weak 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