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

qwen3.8-27b-nvfp4-budget

LM-STUDIO GGUF

qwen35 · 27B

Excellent

Aug 20, 2026 · AMD Ryzen 7 9700X 8-Core Processor

Global Score
79 vs 89
Hardware Fit
57 vs 96
Quality Score
89 vs 86

Hardware

qwen3.5:27b qwen3.8-27b-nvfp4-…
MachineAZW GTR ProMicro-Star International Co., Ltd. MS-7E51
CPUAMD RYZEN AI MAX+ 395 w/ Radeon 8060SAMD Ryzen 7 9700X 8-Core Processor
Cores3216
RAM125 GB31 GB
GPUIntegrated / Apple SiliconNVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modeperformancebalanced

Performance

qwen3.5:27b qwen3.8-27b-nvfp4-…
Tokens/sec10.748.5
First chunk341 ms39 ms
TTFT341 ms283 ms
Load time10.2 sN/A
Memory usage39.7 GB13.7 GB
Memory %32%44%

HW Fit Score Breakdown

qwen3.5:27b

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

qwen3.8-27b-nvfp4-budget

Speed
50/50
TTFT
20/20
Memory
26/30

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

qwen3.8-27b-nvfp4-budget

Reasoning
16/20
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
View qwen3.5:27b details | View qwen3.8-27b-nvfp4-… 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