hf.co/unsloth/Qwen3.8-27B-GGUF:UD-IQ2_XXS
OLLAMA GGUFqwen35 · 27.3B · unknown
Aug 22, 2026 · Apple M1 Pro
llama3.3:70b
OLLAMA GGUFllama · 70.6B · Q4_K_M
Jun 26, 2026 · Cortex-X925
Global Score
31 vs 73
Hardware Fit
37 vs 51
Quality Score
28 vs 83
Hardware
hf.co/unsloth/Qwen… llama3.3:70b
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… llama3.3:70b
Tokens/sec5.44.6
First chunk5076 ms560 ms
TTFT5.1 s560 ms
Load time0.3 s13.8 s
Memory usage11.6 GB49.5 GB
Memory %72%41%
HW Fit Score Breakdown
hf.co/unsloth/Qwen3.8-2…
Speed
13/50
TTFT
10/20
Memory
14/30
llama3.3:70b
Speed
4/50
TTFT
20/20
Memory
27/30
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
llama3.3:70b
Reasoning
17/20
Coding
18/20
Instruction
12/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate 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