Back to leaderboard

Qwen3.8-27B-Ridge-3.7bpw_empero.ai:latest

OLLAMA GGUF

qwen35 · 27.3B · IQ2_M

Good

Aug 27, 2026 · AMD Ryzen 7 9700X 8-Core Processor

llama3.2:3b

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

Aug 28, 2026 · Intel Core™ i5-10210U

Global Score
75 vs 67
Hardware Fit
99 vs 77
Quality Score
64 vs 63

Hardware

Qwen3.8-27B-Ridge-… llama3.2:3b
MachineMicro-Star International Co., Ltd. MS-7E51LENOVO 20U30029MB
CPUAMD Ryzen 7 9700X 8-Core ProcessorIntel Core™ i5-10210U
Cores168
RAM31 GB15 GB
GPUNVIDIA GeForce RTX 5080, AMD Radeon(TM) GraphicsCometLake-U GT2 [UHD Graphics]
OSMicrosoft Windows 11 Pro 10.0.26200Pop 24.04 LTS
Archx64x64
Power Modebalancedlow-power

Performance

Qwen3.8-27B-Ridge-… llama3.2:3b
Tokens/sec60.310.0
First chunk154 ms1166 ms
TTFT154 ms1.2 s
Load time0.0 s6.8 s
Memory usage11.0 GB3.8 GB
Memory %35%25%

HW Fit Score Breakdown

Qwen3.8-27B-Ridge-3.7bp…

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

llama3.2:3b

Speed
27/50
TTFT
20/20
Memory
30/30

Quality

Qwen3.8-27B-Ridge-3.7bp…

Reasoning
20/20
Coding
17/20
Instruction
6/20
Structured
1/15
Math
14/15
Multilingual
6/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Adequate

llama3.2:3b

Reasoning
11/20
Coding
15/20
Instruction
13/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong

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