Local AI Stats.
Skip to content

OVRLab · MODEL RECORD

Granite concision edit

Granite concision edit has 1.335 billion total parameters. The selected F16 GGUF file is 2.673 GB.

Data snapshot: . 1 published test in this catalog.

Model file and details

Provider
OVRLab
Total parameters
1,334,628,352
Exact file size
2,672,668,992 bytes
Quantization / precision
F16
Weight repository
OVRLab/granite-3.1-1b-a400m-concision-experiment
Original model repository
OVRLab/granite-3.1-1b-a400m-concision-experiment
Weight revision
486417a20d43d4232ba9733954ed1ab2bdf03934
Model revision
486417a20d43d4232ba9733954ed1ab2bdf03934
Runtime notes
Confirm model architecture and quantization support in your runner.
Recorded release date
2026-09-20
Date evidence
Source repository createdAt (release-date proxy)

edited.f16.gguf

GGUF file and download on Hugging Face · Original model card

Published benchmark results

These scores were compiled from the linked sources. These published scores were not independently tested here. Different prompts, precision, thinking budgets and tools can change results.

GSM8K · OVR 50

44 / 100

OVR zero-shot evaluation on 50 questions, edited model. Small subset, not the whole benchmark.

Benchmark efficiency: 16.463 published score points per GB of selected weights. This ratio is not an inference-speed measure; check the test settings to see whether the score covers the selected quantization.

Test settings: Edited model, 50-question zero-shot GSM8K subset: 22/50. Base results and the unevaluated control are not used.

Published result for the original model; this selected GGUF file was not separately benchmarked. Different prompts, precision and thinking settings can affect comparisons.

Read the GSM8K · OVR 50 source

Memory and comparison limits

Context and version evidence: The repository and file name identify the selected model. Revision hashes are shown above when recorded. Tested context length, full hardware configuration and run date are not consistently recorded in this snapshot. Only settings explicitly stated in each benchmark record are known.

The 2.673 GB figure covers model weights in this file. It excludes the context cache, runtime, operating system and any separate multimodal files. It is not a measured RAM requirement or a token-generation speed.

Use the model ranking chart to compare one test at a time. Use the 8, 16 and 32 GB memory guide. Check hardware memory and bandwidth before choosing a model.

Need a computer for Granite concision edit?

These complete configurations pass the initial weight-size check for the selected 2.67 GB file. Allow extra memory for context and software. Check the model’s runtime notes and your inference software before buying.

CPU inference

Glorlin Ryzen 7 6800H Mini PC

Ryzen 7 6800H, Radeon 680M, 16GB LPDDR5-6400, 512GB SSD

$469.99Dated reference · not a live offer

16 GB system RAM · CPU planning

The LPDDR5 memory is listed with a 16GB maximum; no RAM upgrade is assumed.

Check price on Amazon ↗Specifications & model limits
Listing and price evidence

Listing evidence: 2026-09-25. Amazon.com base price visible in an owner-supplied screenshot reviewed 25 Sep 2026; capture time not supplied. Dated reference, not a live quote. Excludes card signup offers, coupons, tax and shipping.

Apple unified memory

Apple Mac mini M5 Pro · 24GB

15-core CPU, 16-core GPU, 24GB unified memory, 512GB SSD

$1,699.00Dated reference · not a live offer

24 GB unified memory

Fixed 24GB memory and internal storage limit model size; no CUDA support; Amazon main-offer price and stock were not verified in this run.

Check price on Amazon ↗Specifications & model limits
Listing and price evidence

Listing evidence: 2026-10-03. Apple US launch price announced 22 September 2026: USD 1,699. Dated manufacturer reference, not an Amazon offer; tax and shipping may differ.

AMD unified memory

GMKtec EVO-X2

Ryzen AI Max+ 395, 64GB LPDDR5X-8000, 1TB PCIe 4.0 SSD

$2,199.99Dated reference · not a live offer

64 GB unified memory

Memory is soldered and shared with the operating system.

Check price on Amazon ↗Specifications & model limits
Listing and price evidence

Listing evidence: 2026-09-24. GMKtec, EVO-X2 / 64GB / 1TB, recorded 22 Sep 2026; exact ASIN capacity identified 24 Sep. This is a dated reference, not a current Amazon price; tax, shipping and bundle contents may differ.

Memory matches are estimates, not tested compatibility or speed. As an Amazon Associate I earn from qualifying purchases.

Compare more computers for this model

RAM and VRAM planning for Granite concision edit

Confirm model architecture and quantization support in your runner. The selected weights use 2.673 GB; this excludes context cache, runtime buffers and other programs.

System RAM (CPU inference)
6 GB planning tier · 4 GB initial weight budget
Dedicated VRAM
4 GB planning tier · 3 GB initial weight budget
Unified memory
6 GB planning tier · 4 GB initial weight budget

These are the first listed tiers that pass our reserve policy, not measured minimum requirements. System RAM and VRAM remain separate. Use the memory tool to change the reserve for your context and runner.

Related models with shared benchmark coverage

    Compare by memory and task · Browse the full model directory