Back to leaderboard

qwen3.5:27b

OLLAMA GGUF

qwen35 · 27.8B · Q4_K_M

Good

Mar 6, 2026 · AMD RYZEN AI MAX+ 395 w/ Radeon 8060S

nemotron-3-nano:4b

OLLAMA GGUF

nemotron_h · 4.0B · Q4_K_M

Excellent

Oct 12, 2026 · AMD Ryzen 5 5500

Global Score
79 vs 95
Hardware Fit
57 vs 99
Quality Score
89 vs 93

Hardware

qwen3.5:27b nemotron-3-nano:4b
MachineAZW GTR ProMicrosoft WSL
CPUAMD RYZEN AI MAX+ 395 w/ Radeon 8060SAMD Ryzen 5 5500
Cores3212
RAM125 GB8 GB
GPUIntegrated / Apple SiliconIntegrated / Unknown
OSUbuntu 24.04.4 LTSUbuntu 26.04.1 LTS
Archx64x64
Power Modeperformanceunknown

Performance

qwen3.5:27b nemotron-3-nano:4b
Tokens/sec10.7107.6
First chunk341 ms361 ms
TTFT341 ms1.1 s
Load time10.2 s7.9 s
Memory usage39.7 GB2.6 GB
Memory %32%34%

HW Fit Score Breakdown

qwen3.5:27b

Speed
9/50
TTFT
20/20
Memory
28/30

nemotron-3-nano:4b

Speed
50/50
TTFT
20/20
Memory
29/30

Quality

qwen3.5:27b

Reasoning
17/20
Coding
19/20
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

nemotron-3-nano:4b

Reasoning
19/20
Coding
16/20
Instruction
18/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.5:27b details | View nemotron-3-nano:4b 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