hf.co/unsloth/Qwen3.8-27B-GGUF:UD-IQ1_S
OLLAMA GGUFqwen35 · 27.3B · unknown
Aug 26, 2026 · Apple M1 Pro
nous-hermes2:latest
OLLAMA GGUFllama · 11B · Q4_0
Mar 1, 2026 · Apple M4
Global Score
22 vs 68
Hardware Fit
46 vs 87
Quality Score
12 vs 60
Hardware
hf.co/unsloth/Qwen… nous-hermes2:latest
MachineMacBook ProMacBook Air
CPUApple M1 ProApple M4
Cores1010
RAM16 GB32 GB
GPUApple M1 ProApple M4
OSmacOS 26.6.2macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
hf.co/unsloth/Qwen… nous-hermes2:latest
Tokens/sec6.115.9
First chunk3259 msN/A
TTFT3.3 s345 ms
Load time7.0 s0.4 s
Memory usage10.6 GB6.6 GB
Memory %66%21%
HW Fit Score Breakdown
hf.co/unsloth/Qwen3.8-2…
Speed
15/50
TTFT
14/20
Memory
17/30
nous-hermes2:latest
Speed
27/50
TTFT
30/20
Memory
30/30
Quality
hf.co/unsloth/Qwen3.8-2…
Reasoning
1/20
Coding
1/20
Instruction
3/20
Structured
0/15
Math
5/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Weak Multilingual: Poor
nous-hermes2:latest
Reasoning
11/20
Coding
9/20
Instruction
12/20
Structured
15/15
Math
4/15
Multilingual
9/10
Reasoning: Adequate Coding: Weak 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