Back to leaderboard

devstral:24b

OLLAMA GGUF

llama · 23.6B · Q4_K_M

Excellent

Sep 15, 2026 · Intel Core™ i5-14400F

huihui-qwen3.6-35b-a3b-claude-4.7-opus-abliterated-mtp

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K

Excellent

Jun 12, 2026 · AMD Ryzen 5 5600X 6-Core Processor

Global Score
80 vs 88
Hardware Fit
79 vs 94
Quality Score
80 vs 85

Hardware

devstral:24b huihui-qwen3.6-35b…
MachineGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4Gigabyte Technology Co., Ltd. B550M AORUS PRO
CPUIntel Core™ i5-14400FAMD Ryzen 5 5600X 6-Core Processor
Cores1612
RAM32 GB47 GB
GPUNVIDIA GeForce RTX 5060 TiAD106 [GeForce RTX 4060 Ti]
OSMicrosoft Windows 11 Professionnel 10.0.26200cachyos rolling
Archx64x64
Power Modebalancedlow-power

Performance

devstral:24b huihui-qwen3.6-35b…
Tokens/sec20.239.8
First chunk137 ms3 ms
TTFT137 ms479 ms
Load time9.6 sN/A
Memory usage14.2 GB24.4 GB
Memory %45%52%

HW Fit Score Breakdown

devstral:24b

Speed
33/50
TTFT
20/20
Memory
26/30

huihui-qwen3.6-35b-a3b-…

Speed
50/50
TTFT
20/20
Memory
24/30

Quality

devstral:24b

Reasoning
16/20
Coding
17/20
Instruction
13/20
Structured
15/15
Math
9/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

huihui-qwen3.6-35b-a3b-…

Reasoning
18/20
Coding
17/20
Instruction
13/20
Structured
14/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong 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