arcflare_
Chat32B official

granite-4.0-h-small

by IBM

32B-parameter long-context instruct model with improved instruction following and tool calling, finetuned from Granite-4.0-H-Small-Base.

#chat#instruct#large
arcflare pull ibm-granite/granite-4.0-h-small-GGUF:Q4_K_M

[ 01 ] // quickstart

┌─ arcflare — zsh // tty1
$ 

[ 02 ] // readme

granite-4.0-h-small

32B-parameter long-context instruct model with improved instruction following and tool calling, finetuned from Granite-4.0-H-Small-Base.

Get it

arcflare pull ibm-granite/granite-4.0-h-small-GGUF:Q4_K_M
arcflare run granite-4.0-h-small

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: 19.5 GB. Also published: Q3_K_M (15.4 GB), Q5_K_M (22.9 GB), Q8_0 (34.3 GB)
  • Trained for a 128K context
  • Licence: Apache-2.0. Read it before commercial use

Sizes

  • 32b · 19.5GB

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

[ 03 ] // relatedmore →

llama3.3-70b

Meta

Chat

Meta's 70B multilingual instruction-tuned text model with 128k context, optimized for multilingual dialogue use cases.

size
70B
vram
~44 GB
license
Llama 3.3 Community

1.8× a 24 GB card

#chat #instruct #large

qwen3-32b

Alibaba Qwen

Chat

Qwen3 32.8B dense model switching between thinking and non-thinking modes; 32K context, 131K with YaRN, 100+ languages.

size
32B
vram
~21 GB
license
Apache-2.0

88% of a 24 GB card

#chat #instruct #large

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