Back to leaderboard

codestral:latest

OLLAMA GGUF

llama · 22.2B · Q4_0

Good

Sep 15, 2026 · Intel Core™ i5-14400F

qwen3.5-35b-a3b-t48-c8k:latest

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Sep 6, 2026 · Intel Xeon® E5-4650 v2

Global Score
76 vs 81
Hardware Fit
91 vs 63
Quality Score
69 vs 88

Hardware

codestral:latest qwen3.5-35b-a3b-t4…
MachineGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4Dell Inc. PowerEdge R820
CPUIntel Core™ i5-14400FIntel Xeon® E5-4650 v2
Cores1680
RAM32 GB256 GB
GPUNVIDIA GeForce RTX 5060 TiMicrosoft Remote Display Adapter, NVIDIA Tesla P4, NVIDIA Tesla P4, Microsoft Basic Display Adapter
OSMicrosoft Windows 11 Professionnel 10.0.26200Microsoft Windows Server 2022 Datacenter 10.0.20348
Archx64x64
Power Modebalancedbalanced

Performance

codestral:latest qwen3.5-35b-a3b-t4…
Tokens/sec27.417.2
First chunk86 ms845 ms
TTFT86 ms845 ms
Load time7.2 s103.1 s
Memory usage12.6 GB21.9 GB
Memory %40%9%

HW Fit Score Breakdown

codestral:latest

Speed
43/50
TTFT
20/20
Memory
28/30

qwen3.5-35b-a3b-t48-c8k…

Speed
16/50
TTFT
17/20
Memory
30/30

Quality

codestral:latest

Reasoning
11/20
Coding
17/20
Instruction
11/20
Structured
13/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

qwen3.5-35b-a3b-t48-c8k…

Reasoning
17/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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