Skip to content
Weights Not Walls
Menu

ibm-granite

granite-4.2-8b

Reviewed
Size
8.8B parameterscounted from the safetensors header on the Hub
Licence
unknown, Apache License 2.0Our reading, check the licence: You can use, change and redistribute the model, including commercially. Keep the licence and any notices, and say which files you changed; you do not have to publish your changes. It includes a patent licence that ends for anyone who sues over patents in the work.
On the Hub since
7 Aug 2026the date the repo was created
Context length
128k tokensfrom the model's config
Fine-tune
of ibm-granite/granite-4.1-8b-baseGraniteForCausalLM
On Hugging Face
ibm-granite/granite-4.2-8b58k downloads in the last 30 days, 128 likes

Scores

No independent scores for this model in Epoch AI's data. A score is only shown here when Epoch's name for a model matches this repo with certainty; an uncertain match is left out rather than guessed.

Claimed by the maker Claimed

The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.

Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.

Run it yourself

file sizes read from the Hub 19 Nov 2026

Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 1.3 GB, worked out from the model's config (ibm-granite/granite-4.2-8b), at 16-bit precision. Choose a machine above to see a verdict for each format. Method

GGUF for llama.cpp, Ollama, LM Studio and others

ibm-granite/granite-4.2-8b-GGUF (the maker's own conversion), 281k downloads. Sizes are the real files on the Hub, all parts added up.

FormatSizeMemory neededGet it
Q3_K_S3.7 GBfile size5.4 GB3.7 + 1.3 + 0.50
Commands
llama.cpp
llama-server -hf ibm-granite/granite-4.2-8b-GGUF:Q3_K_S
Ollama
ollama run hf.co/ibm-granite/granite-4.2-8b-GGUF:Q3_K_S
Download
hf download ibm-granite/granite-4.2-8b-GGUF --include "granite-4.2-8b-Q3_K_S.gguf" --local-dir granite-4.2-8b-GGUF
Q3_K_M4.0 GBfile size5.8 GB4.0 + 1.3 + 0.50
Commands
llama.cpp
llama-server -hf ibm-granite/granite-4.2-8b-GGUF:Q3_K_M
Ollama
ollama run hf.co/ibm-granite/granite-4.2-8b-GGUF:Q3_K_M
Download
hf download ibm-granite/granite-4.2-8b-GGUF --include "granite-4.2-8b-Q3_K_M.gguf" --local-dir granite-4.2-8b-GGUF
Q3_K_L4.4 GBfile size6.1 GB4.4 + 1.3 + 0.50
Commands
llama.cpp
llama-server -hf ibm-granite/granite-4.2-8b-GGUF:Q3_K_L
Ollama
ollama run hf.co/ibm-granite/granite-4.2-8b-GGUF:Q3_K_L
Download
hf download ibm-granite/granite-4.2-8b-GGUF --include "granite-4.2-8b-Q3_K_L.gguf" --local-dir granite-4.2-8b-GGUF
Q4_04.7 GBfile size6.5 GB4.7 + 1.3 + 0.50
Commands
llama.cpp
llama-server -hf ibm-granite/granite-4.2-8b-GGUF:Q4_0
Ollama
ollama run hf.co/ibm-granite/granite-4.2-8b-GGUF:Q4_0
Download
hf download ibm-granite/granite-4.2-8b-GGUF --include "granite-4.2-8b-Q4_0.gguf" --local-dir granite-4.2-8b-GGUF
Q4_K_S4.7 GBfile size6.5 GB4.7 + 1.3 + 0.50
Commands
llama.cpp
llama-server -hf ibm-granite/granite-4.2-8b-GGUF:Q4_K_S
Ollama
ollama run hf.co/ibm-granite/granite-4.2-8b-GGUF:Q4_K_S
Download
hf download ibm-granite/granite-4.2-8b-GGUF --include "granite-4.2-8b-Q4_K_S.gguf" --local-dir granite-4.2-8b-GGUF
Q4_K_M5.0 GBfile size6.7 GB5.0 + 1.3 + 0.50
Commands
llama.cpp
llama-server -hf ibm-granite/granite-4.2-8b-GGUF:Q4_K_M
Ollama
ollama run hf.co/ibm-granite/granite-4.2-8b-GGUF:Q4_K_M
Download
hf download ibm-granite/granite-4.2-8b-GGUF --include "granite-4.2-8b-Q4_K_M.gguf" --local-dir granite-4.2-8b-GGUF
Q4_15.2 GBfile size6.9 GB5.2 + 1.3 + 0.50
Commands
llama.cpp
llama-server -hf ibm-granite/granite-4.2-8b-GGUF:Q4_1
Ollama
ollama run hf.co/ibm-granite/granite-4.2-8b-GGUF:Q4_1
Download
hf download ibm-granite/granite-4.2-8b-GGUF --include "granite-4.2-8b-Q4_1.gguf" --local-dir granite-4.2-8b-GGUF
Q5_05.7 GBfile size7.4 GB5.7 + 1.3 + 0.50
Commands
llama.cpp
llama-server -hf ibm-granite/granite-4.2-8b-GGUF:Q5_0
Ollama
ollama run hf.co/ibm-granite/granite-4.2-8b-GGUF:Q5_0
Download
hf download ibm-granite/granite-4.2-8b-GGUF --include "granite-4.2-8b-Q5_0.gguf" --local-dir granite-4.2-8b-GGUF
Q5_K_S5.7 GBfile size7.4 GB5.7 + 1.3 + 0.50
Commands
llama.cpp
llama-server -hf ibm-granite/granite-4.2-8b-GGUF:Q5_K_S
Ollama
ollama run hf.co/ibm-granite/granite-4.2-8b-GGUF:Q5_K_S
Download
hf download ibm-granite/granite-4.2-8b-GGUF --include "granite-4.2-8b-Q5_K_S.gguf" --local-dir granite-4.2-8b-GGUF
Q5_K_M5.8 GBfile size7.6 GB5.8 + 1.3 + 0.50
Commands
llama.cpp
llama-server -hf ibm-granite/granite-4.2-8b-GGUF:Q5_K_M
Ollama
ollama run hf.co/ibm-granite/granite-4.2-8b-GGUF:Q5_K_M
Download
hf download ibm-granite/granite-4.2-8b-GGUF --include "granite-4.2-8b-Q5_K_M.gguf" --local-dir granite-4.2-8b-GGUF
Q5_16.2 GBfile size7.9 GB6.2 + 1.3 + 0.50
Commands
llama.cpp
llama-server -hf ibm-granite/granite-4.2-8b-GGUF:Q5_1
Ollama
ollama run hf.co/ibm-granite/granite-4.2-8b-GGUF:Q5_1
Download
hf download ibm-granite/granite-4.2-8b-GGUF --include "granite-4.2-8b-Q5_1.gguf" --local-dir granite-4.2-8b-GGUF
Q6_K6.7 GBfile size8.5 GB6.7 + 1.3 + 0.50
Commands
llama.cpp
llama-server -hf ibm-granite/granite-4.2-8b-GGUF:Q6_K
Ollama
ollama run hf.co/ibm-granite/granite-4.2-8b-GGUF:Q6_K
Download
hf download ibm-granite/granite-4.2-8b-GGUF --include "granite-4.2-8b-Q6_K.gguf" --local-dir granite-4.2-8b-GGUF
Q8_08.7 GBfile size10.5 GB8.7 + 1.3 + 0.50
Commands
llama.cpp
llama-server -hf ibm-granite/granite-4.2-8b-GGUF:Q8_0
Ollama
ollama run hf.co/ibm-granite/granite-4.2-8b-GGUF:Q8_0
Download
hf download ibm-granite/granite-4.2-8b-GGUF --include "granite-4.2-8b-Q8_0.gguf" --local-dir granite-4.2-8b-GGUF
BF1616.4 GBfile size18.1 GB16.4 + 1.3 + 0.50
Commands
llama.cpp
llama-server -hf ibm-granite/granite-4.2-8b-GGUF:BF16
Ollama
ollama run hf.co/ibm-granite/granite-4.2-8b-GGUF:BF16
Download
hf download ibm-granite/granite-4.2-8b-GGUF --include "granite-4.2-8b-bf16.gguf" --local-dir granite-4.2-8b-GGUF

MLX for Apple silicon

FormatSizeMemory neededRepo
MLXibm-granite/granite-4.2-8b-q4-mlx4.6 GBfile size6.4 GB4.6 + 1.3 + 0.50Download page
MLXibm-granite/granite-4.2-8b-q8-mlx8.7 GBfile size10.4 GB8.7 + 1.3 + 0.50Download page

Original weights size from the safetensors header, for vLLM, SGLang, Transformers

FormatSizeMemory neededRepo
BF16original weights16.4 GBfile size18.1 GB16.4 + 1.3 + 0.50
hf download ibm-granite/granite-4.2-8b --local-dir granite-4.2-8b
Other conversions (6; sizes not read)

The Hub tags 66 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.

Run it by API

Hugging Face Inference Providers, fetched 19 Nov 2026, 13:58 UTC

2 providers serve this model through the Hugging Face router. Prices are US dollars per million tokens. Precision is what the provider reports; a lower precision than the original weights can change answers. Live first, then cheapest output.

ProviderInOutContextPrecisionTokens/sFirst tokenUptime 24hToolsJSON
CoreWeave$0.06$0.15128kbf16910.2 s99.2%yesyes
DeepInfra$0.06$0.25128kbf16900.5 s100.0%yesno

Through the router, with a Hugging Face token (the router bills your Hugging Face account). Change the name after the colon to pick another provider.

curl https://router.huggingface.co/v1/chat/completions \ -H "Authorization: Bearer $HF_TOKEN" -H "Content-Type: application/json" \ -d '{"model": "ibm-granite/granite-4.2-8b:coreweave", "messages": [{"role": "user", "content": "Hello"}]}'

Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.

Planned for this page Not built yet

Try it in private chat
A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
Fine-tune it
Fine-tuning a few base models from this page and publishing the result here.
Creators and earnings
Pages for people who publish fine-tunes and adapters of this model, and what they earn.
Fund and bounties
Bounties for new open models, paid from a public fund. How the fund will work.
Contribute compute
How to give compute to open model work, with Akash.

Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.