Skip to content
Local AI Wizard
Your machine
Theme

bigstral-12b-32k

abacusai · abacusai/bigstral-12b-32k

Weights license: Apache 2.0 · code and components may use other terms

Reported by the publisher13 resultsabacusai's model card · read 2026-10-25 · not ranked · see them
Memory needed~10 GBQ4 weights + working room, before the machine's reserve
Parameters12.5 BHub safetensors total
Repository updated2024-09-09A commit is not a release date

Quality

No comparable score

We track no public, comparable benchmark that covers this model yet. No score is inferred.

Reported by the publisher

13 results · abacusai's model card · read 2026-10-25
IFEval (0-Shot) (strict accuracy)
41.94Text Generation · 0-shot
BBH (3-Shot) (normalized accuracy)
25.56Text Generation · 3-shot
MATH Lvl 5 (4-Shot) (exact match)
0.98Text Generation · 4-shot
GPQA (0-shot) (acc_norm)
5.7Text Generation · 0-shot
MuSR (0-shot) (acc_norm)
15.86Text Generation · 0-shot
MMLU-PRO (5-shot) (main; test; accuracy)
18.24Text Generation · 5-shot
Avg.
18.05Open LLM Leaderboard Evaluation Results
IFEval (0-Shot)
41.94Open LLM Leaderboard Evaluation Results · 0-shot
Every reported result13
BBH (3-Shot)
25.56Open LLM Leaderboard Evaluation Results · 3-shot
MATH Lvl 5 (4-Shot)
0.98Open LLM Leaderboard Evaluation Results · 4-shot
GPQA (0-shot)
5.70Open LLM Leaderboard Evaluation Results · 0-shot
MuSR (0-shot)
15.86Open LLM Leaderboard Evaluation Results · 0-shot
MMLU-PRO (5-shot)
18.24Open LLM Leaderboard Evaluation Results · 5-shot

Values as printed on the card, with the publisher's own settings (card section: Open LLM Leaderboard Evaluation Results). Not comparable across publishers and not used in any ranking. Model card

Runs on

Fast memory holds it 90

The planning estimate fits the memory the model can use quickly: graphics card VRAM, or unified memory within the macOS GPU share.

Show all 90

Within memory, outside the fast part 26

Within the machine's memory, outside its fast part: on a graphics card the layers that do not fit run on the CPU from PC RAM (the listed RAM, or 32 GB assumed); on a Mac, above the macOS default GPU share. Not a speed figure.

Show all 26

One memory tier short 3

The same machines with the next memory size up would hold it in fast memory.

Hardware profiles grouped by the Q4 planning estimate on each machine (dedicated GPUs reserve 2 GB; unified and system memory 25%, 2 to 8 GB): the fast memory holds it, it is within memory but outside the fast part (layers offloaded to PC RAM, or above the macOS GPU share), or the machine is one memory tier short. Not a measured fit or speed.

Measured speed

No published measurement for this checkpoint

Tokens per second are shown only when a source publishes them with hardware, build and setup. They are never estimated.

How to run

Runtime compatibility and tokens per second have not been measured for this entry. Published metadata and a memory estimate do not prove a successful local run.

Library in source: transformers

Choose my computer

Technical details

What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.

Checkpoint / source
abacusai/bigstral-12b-32k
Task
text-generation
Architecture
MistralForCausalLM
Library in source
transformers
Weight license
Apache 2.0
Commercial use
Allowed Apache License 2.0 text (SPDX) · read 2026-10-18license text
Every stored field13 fields
Revision checked
cf85301bc4deed33852c292cc6d6ae8ff946c129
Architecture
MistralForCausalLM
Library
transformers
Hub task tag
text-generation
Declared base models
mistralai/Mistral-7B-Instruct-v0.2
Formats
safetensors
Access
Open download
Publisher kind
Official
Tensor evidence
floating-tensor-elements · 12.48B · F16checked 2026-09-26
Repository created
2024-03-06creation is not the model's release
Repository updated
2024-09-09a commit is not a release date
Hub downloads (30 days) · likes
8,843 · 44this repository only · read 2026-10-25
Catalog state
Hub config or weights found; no inventory benchmark link

Sources

Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.

Valid source snapshot: 2026-09-26. This source record has not received a complete technical review. Missing data remain unknown; a repository commit is not a model release date.