Back to leaderboard

codestral:22b

OLLAMA GGUF

llama · 22.2B · Q4_0

Good

Jun 26, 2026 · Cortex-X925

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

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

Hardware

codestral:22b Qwen3.8-27B-Ridge-…
MachineNVIDIA NVIDIA_DGX_SparkMicro-Star International Co., Ltd. MS-7E51
CPUCortex-X925AMD Ryzen 7 9700X 8-Core Processor
Cores2016
RAM122 GB31 GB
GPUDevice 2e12NVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modeperformancebalanced

Performance

codestral:22b Qwen3.8-27B-Ridge-…
Tokens/sec17.260.3
First chunk129 ms154 ms
TTFT129 ms154 ms
Load time11.6 s0.0 s
Memory usage18.9 GB11.0 GB
Memory %16%35%

HW Fit Score Breakdown

codestral:22b

Speed
17/50
TTFT
20/20
Memory
30/30

Qwen3.8-27B-Ridge-3.7bp…

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

Quality

codestral:22b

Reasoning
11/20
Coding
17/20
Instruction
9/20
Structured
14/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Weak Structured Output: Strong Math: Weak Multilingual: Strong

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

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