Back to leaderboard

qwen3:8b

OLLAMA GGUF

qwen3 · 8.2B · Q4_K_M

Excellent

Mar 5, 2026 · Intel Core™ Ultra 9 285K

codestral:22b

OLLAMA GGUF

llama · 22.2B · Q4_0

Good

Jun 26, 2026 · Cortex-X925

Global Score
84 vs 67
Hardware Fit
97 vs 67
Quality Score
79 vs 67

Hardware

qwen3:8b codestral:22b
MachineASUSNVIDIA NVIDIA_DGX_Spark
CPUIntel Core™ Ultra 9 285KCortex-X925
Cores2420
RAM47 GB122 GB
GPUNVIDIA GeForce RTX 5090, Intel(R) GraphicsDevice 2e12
OSMicrosoft Windows 11 Pro 10.0.26200Ubuntu 24.04.4 LTS
Archx64arm64
Power Modebalancedperformance

Performance

qwen3:8b codestral:22b
Tokens/sec208.017.2
First chunk82 ms129 ms
TTFT1.3 s129 ms
Load time1.5 s11.6 s
Memory usage9.6 GB18.9 GB
Memory %20%16%

HW Fit Score Breakdown

qwen3:8b

Speed
50/50
TTFT
18/20
Memory
29/30

codestral:22b

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

Quality

qwen3:8b

Reasoning
18/20
Coding
10/20
Instruction
14/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

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
View qwen3:8b details | View codestral:22b 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