hf.co/unsloth/Qwen3.8-27B-GGUF:UD-IQ1_S
OLLAMA GGUFqwen35 · 27.3B · unknown
Aug 25, 2026 · Apple M1 Pro
llama3.2:3b
OLLAMA GGUFllama · 3.2B · Q4_K_M
Jun 25, 2026 · Cortex-A78AE
Global Score
46 vs 74
Hardware Fit
50 vs 99
Quality Score
44 vs 63
Hardware
hf.co/unsloth/Qwen… llama3.2:3b
MachineMacBook ProNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUApple M1 ProCortex-A78AE
Cores106
RAM16 GB7 GB
GPUApple M1 ProIntegrated / Unknown
OSmacOS 26.6.2Ubuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced
Performance
hf.co/unsloth/Qwen… llama3.2:3b
Tokens/sec6.021.1
First chunk2377 ms1032 ms
TTFT2.2 s1.0 s
Load time6.8 s8.4 s
Memory usage10.6 GB2.4 GB
Memory %66%32%
HW Fit Score Breakdown
hf.co/unsloth/Qwen3.8-2…
Speed
15/50
TTFT
18/20
Memory
17/30
llama3.2:3b
Speed
50/50
TTFT
20/20
Memory
29/30
Quality
hf.co/unsloth/Qwen3.8-2…
Reasoning
8/20
Coding
5/20
Instruction
10/20
Structured
11/15
Math
3/15
Multilingual
7/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Adequate
llama3.2:3b
Reasoning
10/20
Coding
14/20
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
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