Back to leaderboard

Mixtral-47B:47B

OLLAMA GGUF

llama · 46.7B · Q4_0

Not Rec.

Aug 19, 2026 · Intel Core™ i7-14700F

qwen3.5:35b-a3b-q4_K_M

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Good

Jul 31, 2026 · Intel Core™ i9-14900K

Global Score
55 vs 79
Hardware Fit
55 vs 62
Quality Score
55 vs 86

Hardware

Mixtral-47B:47B qwen3.5:35b-a3b-q4…
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCMicro-Star International Co., Ltd. MS-7D98
CPUIntel Core™ i7-14700FIntel Core™ i9-14900K
Cores2832
RAM64 GB128 GB
GPUNVIDIA GeForce RTX 5080Intel(R) UHD Graphics 770, NVIDIA Quadro K4000
OSMicrosoft Windows 11 Enterprise 10.0.26200Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

Mixtral-47B:47B qwen3.5:35b-a3b-q4…
Tokens/sec6.716.4
First chunk758 ms787 ms
TTFT758 ms787 ms
Load time12.1 s19.3 s
Memory usage25.5 GB21.8 GB
Memory %40%17%

HW Fit Score Breakdown

Mixtral-47B:47B

Speed
7/50
TTFT
20/20
Memory
28/30

qwen3.5:35b-a3b-q4_K_M

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

Quality

Mixtral-47B:47B

Reasoning
9/20
Coding
14/20
Instruction
6/20
Structured
12/15
Math
7/15
Multilingual
7/10
Reasoning: Weak Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Weak Multilingual: Adequate

qwen3.5:35b-a3b-q4_K_M

Reasoning
17/20
Coding
17/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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