Data Sculpting
Inference
Local AI
•
Hardware
•
Models
•
Optimization
•
Community
Portal
Search
Member List
Calendar
Help
Hello There, Guest!
Login
Register
Login
Username:
Password:
Lost Password?
Remember me
Sign in with X.com
Inference
›
Harnesses, Agents & Orchestration
›
MCP / APIs / Tool Calling
model merge got better or just different
Thread Rating:
0 Vote(s) - 0 Average
1
2
3
4
5
Linear Mode
model merge got better or just different
bytestack
Member
Posts: 50
Threads: 3
Joined: Sep 2026
Reputation:
0
#12
09-15-2026, 11:49 AM
That matches what I was seeing. I ended up in about the same place using MLX.
Find
Reply
«
Next Oldest
|
Next Newest
»
Messages In This Thread
model merge got better or just different
- by
mangowire
- 09-12-2026, 11:23 AM
Re: model merge got better or just different
- by
phaseshed
- 09-12-2026, 11:32 PM
Re: model merge got better or just different
- by
circuitworks90
- 09-13-2026, 08:16 AM
Re: model merge got better or just different
- by
routerunner
- 09-13-2026, 08:38 AM
Re: model merge got better or just different
- by
batchscope72
- 09-13-2026, 04:56 PM
Re: model merge got better or just different
- by
batchsize
- 09-13-2026, 05:51 PM
Re: model merge got better or just different
- by
vramstream
- 09-15-2026, 06:39 AM
Re: model merge got better or just different
- by
griffinloom66
- 09-15-2026, 08:50 AM
Re: model merge got better or just different
- by
tensorport
- 09-15-2026, 09:26 AM
Re: model merge got better or just different
- by
localpatch78
- 09-15-2026, 10:14 AM
Re: model merge got better or just different
- by
thetatinker77
- 09-15-2026, 11:20 AM
Re: model merge got better or just different
- by
bytestack
- 09-15-2026, 11:49 AM
Re: model merge got better or just different
- by
mangohouse
- 09-15-2026, 12:57 PM
Re: model merge got better or just different
- by
rocmstack25
- 09-15-2026, 02:03 PM
Re: model merge got better or just different
- by
cacheline
- 09-15-2026, 02:39 PM
View a Printable Version
Forum Jump:
Private Messages
User Control Panel
Who's Online
Search
Forum Home
Announcements
-- Forum Announcements
-- Community Announcements
Hardware
-- GPUs
-- Systems & Builds
-- CPUs / NPUs / Accelerators
Drivers / Frameworks / Toolkits
-- NVIDIA / CUDA
-- AMD / ROCm
-- Apple / MLX
-- PyTorch / JAX / Other Frameworks
Inference Engines
-- llama.cpp / GGUF
-- vLLM / SGLang
-- TensorRT-LLM
-- Ollama / LM Studio / Desktop Runtimes
-- Other Engines
Optimization & Performance
-- Quantization
-- Context / KV Cache
-- Performance Tuning
-- Benchmarks
Harnesses, Agents & Orchestration
-- Agents
-- Routers
-- MCP / APIs / Tool Calling
-- Workflows / Automation
LLM Models
-- Proprietary / Frontier
-- Open Weight
---- Hosted
---- Local
---- Recipes & Configurations
-- Embedding / Reranking Models
Training & Customization
-- Fine-Tuning / LoRA
-- Distillation
-- Dataset Creation / Curation
-- Model Merging
RAG & Knowledge Systems
-- RAG
-- Embeddings
-- Vector Databases
-- Search / Retrieval / Reranking
Prompting & Context Engineering
-- Prompts / System Prompts
-- Structured Output
-- Long Context / Memory
Evaluation & Testing
-- Benchmarks
-- Evals
-- Model Comparisons
-- Quality / Reliability Testing
Generative AI
-- Image
-- Video
-- Audio / Speech
-- Multimodal
Apps / Utilities / Tools
-- Online / Hosted
-- Local
Edge AI & Gadgets
-- Mobile
-- SBCs / Mini PCs
-- AI Devices
Security, Privacy & Safety
-- Local Privacy
-- Model / Agent Security
-- Sandboxing
Miscellaneous Discussion
-- General
-- News & Industry
-- Off Topic
Users browsing this thread: 1 Guest(s)