swift-1.5-iq2_xs
LM-STUDIO UNKNOWNNov 14, 2026 · AMD Ryzen 5 5600X 6-Core Processor
huihui_ai/Qwen3.8-abliterated:27b
OLLAMA GGUFqwen35 · 27.3B · Q4_K_M
Aug 25, 2026 · AMD RYZEN AI MAX+ 395
Global Score
96 vs 80
Hardware Fit
94 vs 65
Quality Score
97 vs 87
Hardware
swift-1.5-iq2_xs huihui_ai/Qwen3.8-…
MachineGigabyte Technology Co., Ltd. B550M AORUS PROAZW GTR Pro
CPUAMD Ryzen 5 5600X 6-Core ProcessorAMD RYZEN AI MAX+ 395
Cores1232
RAM47 GB125 GB
GPUAD106 [GeForce RTX 4060 Ti]Radeon 8060S
OSArch LinuxUbuntu 24.04.4 LTS
Archx64x64
Power Modelow-powerlow-power
Performance
swift-1.5-iq2_xs huihui_ai/Qwen3.8-…
Tokens/sec60.017.5
First chunk2 ms597 ms
TTFT2.6 s597 ms
Load timeN/A7.1 s
Memory usage0.9 GB17.4 GB
Memory %2%14%
HW Fit Score Breakdown
swift-1.5-iq2_xs
Speed
50/50
TTFT
14/20
Memory
30/30
huihui_ai/Qwen3.8-ablit…
Speed
16/50
TTFT
19/20
Memory
30/30
Quality
swift-1.5-iq2_xs
Reasoning
20/20
Coding
19/20
Instruction
19/20
Structured
15/15
Math
15/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
huihui_ai/Qwen3.8-ablit…
Reasoning
17/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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