Back to leaderboard

hf.co/unsloth/Qwen3.8-27B-GGUF:UD-IQ1_S

OLLAMA GGUF

qwen35 · 27.3B · unknown

Not Rec.

Aug 23, 2026 · Apple M1 Pro

codestral:22b

OLLAMA GGUF

llama · 22.2B · Q4_0

Good

Jun 26, 2026 · Cortex-X925

Global Score
22 vs 67
Hardware Fit
46 vs 67
Quality Score
12 vs 67

Hardware

hf.co/unsloth/Qwen… codestral:22b
MachineMacBook ProNVIDIA NVIDIA_DGX_Spark
CPUApple M1 ProCortex-X925
Cores1020
RAM16 GB122 GB
GPUApple M1 ProDevice 2e12
OSmacOS 26.6.2Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance

Performance

hf.co/unsloth/Qwen… codestral:22b
Tokens/sec6.117.2
First chunk3229 ms129 ms
TTFT3.2 s129 ms
Load time6.3 s11.6 s
Memory usage10.6 GB18.9 GB
Memory %66%16%

HW Fit Score Breakdown

hf.co/unsloth/Qwen3.8-2…

Speed
15/50
TTFT
14/20
Memory
17/30

codestral:22b

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

Quality

hf.co/unsloth/Qwen3.8-2…

Reasoning
1/20
Coding
1/20
Instruction
3/20
Structured
0/15
Math
5/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Weak Multilingual: Poor

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

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