hf.co/unsloth/Qwen3.8-27B-GGUF:UD-IQ2_XXS
OLLAMA GGUFqwen35 · 27.3B · unknown
Aug 22, 2026 · Apple M1 Pro
deepseek-coder-v2:16b
OLLAMA GGUFdeepseek2 · 15.7B · Q4_0
Jun 26, 2026 · Cortex-X925
Global Score
31 vs 82
Hardware Fit
37 vs 100
Quality Score
28 vs 74
Hardware
hf.co/unsloth/Qwen… deepseek-coder-v2:…
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… deepseek-coder-v2:…
Tokens/sec5.4117.2
First chunk5076 ms275 ms
TTFT5.1 s275 ms
Load time0.3 s8.9 s
Memory usage11.6 GB17.9 GB
Memory %72%15%
HW Fit Score Breakdown
hf.co/unsloth/Qwen3.8-2…
Speed
13/50
TTFT
10/20
Memory
14/30
deepseek-coder-v2:16b
Speed
50/50
TTFT
20/20
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
deepseek-coder-v2:16b
Reasoning
8/20
Coding
19/20
Instruction
13/20
Structured
12/15
Math
14/15
Multilingual
8/10
Reasoning: Weak 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