Compare models on your machine

Not generic leaderboards: every model is rated for your hardware, your tool and your workload — so you can see which one will actually feel better to use.

Hardware

Use case

Tool

Other apps

Context

Qwen2.5-Coder 7B InstructQwen3.6 35B-A3BQwen3.5 35B-A3BGLM-4.7-Flash (30B-A3B)

MacBook Pro M4 Pro 48 GB · Agentic coding / medium repository

Sort by

Qwen3.6 35B-A3B5-bit · LM StudioComfortableSpeed 50–70 tok/sUses 25 GBFree 12 GB
Qwen3.5 35B-A3B5-bit · LM StudioComfortableSpeed 50–70 tok/sUses 25 GBFree 12 GB
GLM-4.7-Flash (30B-A3B)6-bit · LM StudioComfortableSpeed 35–50 tok/sUses 26 GBFree 10 GB
Qwen2.5-Coder 7B Instruct8-bit · LM StudioAcceptableSpeed 18–25 tok/sUses 11 GBFree 26 GB

Model									Confidence
Qwen3.6 35B-A3B5-bit · LM Studio	Comfortable	25 GB	12 GB	Excellent50–70 tok/s	Comfortable	128K	Strong	Strong	Medium confidence
Qwen3.5 35B-A3B5-bit · LM Studio	Comfortable	25 GB	12 GB	Excellent50–70 tok/s	Comfortable	128K	Good	Good	Medium confidence
GLM-4.7-Flash (30B-A3B)6-bit · LM Studio	Comfortable	26 GB	10 GB	Comfortable35–50 tok/s	Comfortable	128K	Strong	Strong	Medium confidence
Qwen2.5-Coder 7B Instruct8-bit · LM Studio	Acceptable	11 GB	26 GB	Adequate18–25 tok/s	Adequate	32K	Fair	Weak	Medium confidence

Qwen2.5-Coder 7B Instruct

8-bit · LM Studio

Acceptable

Usable for agentic coding, but expect compromises: generation (18–25 tok/s) is adequate but not ideal for agentic coding; ingesting a prompt of 18K tokens takes ≈60 s, and each step ≈30 s — noticeable waits.

MemoryExcellent

≈26 GB headroom

GenerationFair

18–25 tok/s

Prompt processingFair

≈60 s first prompt

ContextPoor

32K context

Tool compatibilityExcellent

Official

Workload suitabilityPoor

Poorly suited

Qwen3.6 35B-A3B

5-bit · LM Studio

Comfortable

Yes — this should be comfortable for agentic coding.

MemoryGood

≈12 GB headroom

GenerationExcellent

50–70 tok/s

Prompt processingGood

≈20 s first prompt

ContextExcellent

32K context

Tool compatibilityExcellent

Official

Workload suitabilityGood

Suited

Qwen3.5 35B-A3B

5-bit · LM Studio

Comfortable

Yes — this should be comfortable for agentic coding.

MemoryGood

≈12 GB headroom

GenerationExcellent

50–70 tok/s

Prompt processingGood

≈20 s first prompt

ContextExcellent

32K context

Tool compatibilityExcellent

Official

Workload suitabilityGood

Suited

GLM-4.7-Flash (30B-A3B)

6-bit · LM Studio

Comfortable

Yes — this should be comfortable for agentic coding.

MemoryGood

≈10 GB headroom

GenerationGood

35–50 tok/s

Prompt processingGood

≈25 s first prompt

ContextGood

32K context

Tool compatibilityExcellent

Official

Workload suitabilityGood

Suited