hf.co/unsloth/Qwen3.8-27B-GGUF:UD-IQ2_XXS
OLLAMA GGUFqwen35 · 27.3B · unknown
Aug 22, 2026 · Apple M1 Pro
vicuna:13b
OLLAMA GGUFllama · 13B · Q4_0
Mar 1, 2026 · Apple M4
Global Score
31 vs 59
Hardware Fit
37 vs 84
Quality Score
28 vs 48
Hardware
hf.co/unsloth/Qwen… vicuna:13b
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… vicuna:13b
Tokens/sec5.413.4
First chunk5076 msN/A
TTFT5.1 s438 ms
Load time0.3 s0.6 s
Memory usage11.6 GB10.3 GB
Memory %72%32%
HW Fit Score Breakdown
hf.co/unsloth/Qwen3.8-2…
Speed
13/50
TTFT
10/20
Memory
14/30
vicuna:13b
Speed
24/50
TTFT
30/20
Memory
30/30
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
vicuna:13b
Reasoning
7/20
Coding
5/20
Instruction
12/20
Structured
13/15
Math
3/15
Multilingual
8/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate 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