Back to leaderboard

mistral:latest

OLLAMA GGUF

llama · 7.2B · Q4_K_M

Good

May 27, 2026 · AMD Ryzen 5 2600X Six-Core Processor

qwen3.8:27b-bf16

OLLAMA GGUF

qwen35 · 27.3B · BF16

Excellent

Aug 22, 2026 · AMD EPYC 7713 64-Core Processor

Global Score
73 vs 85
Hardware Fit
100 vs 77
Quality Score
62 vs 88

Hardware

mistral:latest qwen3.8:27b-bf16
MachineMicro-Star International Co., Ltd. MS-7B79Dell Inc. PowerEdge XE8545
CPUAMD Ryzen 5 2600X Six-Core ProcessorAMD EPYC 7713 64-Core Processor
Cores12128
RAM16 GB1007 GB
GPUNVIDIA GeForce GTX 1080GA100 [A100 SXM4 80GB], GA100 [A100 SXM4 80GB], Integrated Matrox G200eW3 Graphics Controller, GA100 [A100 SXM4 80GB], GA100 [A100 SXM4 80GB]
OSMicrosoft Windows 11 Famille 10.0.26200Rocky Linux 8.10
Archx64x64
Power Modebalancedunknown

Performance

mistral:latest qwen3.8:27b-bf16
Tokens/sec31.727.2
First chunk102 ms237 ms
TTFT102 ms237 ms
Load time14.3 s43.8 s
Memory usage4.8 GB68.8 GB
Memory %30%7%

HW Fit Score Breakdown

mistral:latest

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

qwen3.8:27b-bf16

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

Quality

mistral:latest

Reasoning
8/20
Coding
13/20
Instruction
16/20
Structured
12/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong

qwen3.8:27b-bf16

Reasoning
18/20
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
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest