Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Aug 28, 2026 · Intel Core™ i5-10210U

codestral:22b

OLLAMA GGUF

llama · 22.2B · Q4_0

Good

Jun 26, 2026 · Cortex-X925

Global Score
64 vs 67
Hardware Fit
69 vs 67
Quality Score
62 vs 67

Hardware

qwen3.5:4b codestral:22b
MachineLENOVO 20U30029MBNVIDIA NVIDIA_DGX_Spark
CPUIntel Core™ i5-10210UCortex-X925
Cores820
RAM15 GB122 GB
GPUCometLake-U GT2 [UHD Graphics]Device 2e12
OSPop 24.04 LTSUbuntu 24.04.4 LTS
Archx64arm64
Power Modeperformanceperformance

Performance

qwen3.5:4b codestral:22b
Tokens/sec7.417.2
First chunk1815 ms129 ms
TTFT1.8 s129 ms
Load time10.9 s11.6 s
Memory usage3.5 GB18.9 GB
Memory %23%16%

HW Fit Score Breakdown

qwen3.5:4b

Speed
19/50
TTFT
20/20
Memory
30/30

codestral:22b

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

Quality

qwen3.5:4b

Reasoning
15/20
Coding
14/20
Instruction
6/20
Structured
12/15
Math
6/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Weak 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 qwen3.5:4b 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