Chat7B-A1B official

granite-4-0-h-tiny

by IBM

IBM 7B-parameter (1B active) hybrid long-context instruct model with improved instruction following and tool calling.

#chat #instruct #moe

arcflare pull ibm-granite/granite-4.0-h-tiny-GGUF:Q4_K_M

[ 01 ] // quickstart

┌─ arcflare — zsh // tty1

[ 02 ] // readme

granite-4-0-h-tiny

IBM 7B-parameter (1B active) hybrid long-context instruct model with improved instruction following and tool calling.

Get it

arcflare pull ibm-granite/granite-4.0-h-tiny-GGUF:Q4_K_M

arcflare run granite-4.0-h-tiny

ArcFlare reads the GGUF header and loads it at the largest context your free VRAM can actually hold. Use arcflare fit to see that before downloading anything else, or arcflare use opencode to code with it.

Highlights

Downloads the Q4_K_M file by default: 4.2 GB. Also published: Q8_0 (7.4 GB), Q5_K_M (4.9 GB), Q3_K_M (3.4 GB)
Trained for a 128K context
Licence: Apache-2.0. Read it before commercial use

Sizes

7b-a1b · 4.2GB

Other sizes live in sibling repos: swap the size in the repo name when pulling.

[ 03 ] // relatedmore →

qwen3-30b-a3b-instruct-2507

Alibaba Qwen

Chat

Qwen3-30B-A3B non-thinking update: 30.5B-parameter MoE with 3.3B active, 128 experts and 256K native context.

size: 30B-A3B
vram: ~20 GB
license: Apache-2.0

83% of a 24 GB card

#chat #instruct #moe

ernie-4-5-21b-a3b

Baidu

Chat

Text MoE post-trained model with 21B total and 3B activated parameters per token and a 131072-token context length.

size: 21B-A3B
vram: ~15 GB
license: Apache-2.0

63% of a 24 GB card

#chat #instruct #moe

lfm2-8b-a1b

Liquid AI

Chat

Liquid AI on-device hybrid MoE with 8.3B total and 1.5B active parameters and a 32,768-token context.

size: 8B-A1B
vram: ~6 GB
license: LFM Open License v1.0

25% of a 24 GB card

#chat #instruct #moe