Back to leaderboard

swift-1.5-iq2_xs

LM-STUDIO UNKNOWN
Excellent

Nov 14, 2026 · AMD Ryzen 5 5600X 6-Core Processor

qwen/qwen3.6-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K_M

Excellent

Nov 1, 2026 · AMD RYZEN AI MAX+ 395

Global Score
96 vs 88
Hardware Fit
94 vs 90
Quality Score
97 vs 87

Hardware

swift-1.5-iq2_xs qwen/qwen3.6-35b-a3b
MachineGigabyte Technology Co., Ltd. B550M AORUS PROGMKtec EVO-X3
CPUAMD Ryzen 5 5600X 6-Core ProcessorAMD RYZEN AI MAX+ 395
Cores1232
RAM47 GB120 GB
GPUAD106 [GeForce RTX 4060 Ti]AMD Radeon(TM) 8060S Graphics
OSArch LinuxMicrosoft Windows 11 Pro 10.0.26300
Archx64x64
Power Modelow-powerbalanced

Performance

swift-1.5-iq2_xs qwen/qwen3.6-35b-a3b
Tokens/sec60.049.0
First chunk2 ms44 ms
TTFT2.6 s334 ms
Load timeN/A61.3 s
Memory usage0.9 GB59.8 GB
Memory %2%50%

HW Fit Score Breakdown

swift-1.5-iq2_xs

Speed
50/50
TTFT
14/20
Memory
30/30

qwen/qwen3.6-35b-a3b

Speed
45/50
TTFT
20/20
Memory
25/30

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

qwen/qwen3.6-35b-a3b

Reasoning
16/20
Coding
18/20
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
View swift-1.5-iq2_xs details | View qwen/qwen3.6-35b-a3b details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest