Qwen3.8-27B-Opus-Distill-IQ3_XXS:latest
OLLAMA GGUFqwen35 · 27.3B · IQ3_XXS
Aug 18, 2026 · AMD Ryzen 7 9700X 8-Core Processor
hf.co/LiquidAI/LFM2.5-2.6B-GGUF:F16
OLLAMA GGUFlfm2 · 2.7B · unknown
Aug 25, 2026 · Apple M1 Pro
Global Score
90 vs 61
Hardware Fit
98 vs 97
Quality Score
86 vs 46
Hardware
Qwen3.8-27B-Opus-D… hf.co/LiquidAI/LFM…
MachineMicro-Star International Co., Ltd. MS-7E51MacBook Pro
CPUAMD Ryzen 7 9700X 8-Core ProcessorApple M1 Pro
Cores1610
RAM31 GB16 GB
GPUNVIDIA GeForce RTX 5080, AMD Radeon(TM) GraphicsApple M1 Pro
OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.6.2
Archx64arm64
Power Modebalancedbalanced
Performance
Qwen3.8-27B-Opus-D… hf.co/LiquidAI/LFM…
Tokens/sec61.831.0
First chunk325 ms129 ms
TTFT325 ms129 ms
Load time5.5 s3.5 s
Memory usage12.2 GB6.6 GB
Memory %39%41%
HW Fit Score Breakdown
Qwen3.8-27B-Opus-Distil…
Speed
50/50
TTFT
20/20
Memory
28/30
hf.co/LiquidAI/LFM2.5-2…
Speed
50/50
TTFT
20/20
Memory
27/30
Quality
Qwen3.8-27B-Opus-Distil…
Reasoning
16/20
Coding
17/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
hf.co/LiquidAI/LFM2.5-2…
Reasoning
14/20
Coding
13/20
Instruction
3/20
Structured
0/15
Math
14/15
Multilingual
2/10
Reasoning: Adequate Coding: Adequate Instruction Following: Poor Structured Output: Poor Math: Strong Multilingual: Poor
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