hf.co/unsloth/Qwen3.8-27B-GGUF:UD-IQ2_XXS
OLLAMA GGUFqwen35 · 27.3B · unknown
Aug 22, 2026 · Apple M1 Pro
qwen2.5:72b
OLLAMA GGUFqwen2 · 72.7B · Q4_K_M
Jun 27, 2026 · Cortex-X925
Global Score
31 vs 75
Hardware Fit
37 vs 50
Quality Score
28 vs 86
Hardware
hf.co/unsloth/Qwen… qwen2.5:72b
MachineMacBook ProNVIDIA NVIDIA_DGX_Spark
CPUApple M1 ProCortex-X925
Cores1020
RAM16 GB122 GB
GPUApple M1 ProDevice 2e12
OSmacOS 26.6.2Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance
Performance
hf.co/unsloth/Qwen… qwen2.5:72b
Tokens/sec5.44.4
First chunk5076 ms529 ms
TTFT5.1 s529 ms
Load time0.3 s49.7 s
Memory usage11.6 GB54.0 GB
Memory %72%44%
HW Fit Score Breakdown
hf.co/unsloth/Qwen3.8-2…
Speed
13/50
TTFT
10/20
Memory
14/30
qwen2.5:72b
Speed
4/50
TTFT
20/20
Memory
26/30
Quality
hf.co/unsloth/Qwen3.8-2…
Reasoning
9/20
Coding
2/20
Instruction
1/20
Structured
1/15
Math
9/15
Multilingual
6/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Adequate Multilingual: Adequate
qwen2.5:72b
Reasoning
19/20
Coding
19/20
Instruction
12/20
Structured
14/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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