Skip to content
Local AI Wizard
Your machine
Theme

Smaug-Qwen2-72B-Instruct

abacusai · abacusai/Smaug-Qwen2-72B-Instruct

Weights license: Publisher terms: tongyi-qianwen · code and components may use other terms

Reported by the publisher27 resultsabacusai's model card · read 2026-10-25 · not ranked · see them
Memory needed~55 GBQ4 weights + working room, before the machine's reserve
Parameters72.7 BHub safetensors total
Repository updated2024-08-06A 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

27 results · abacusai's model card · read 2026-10-25
IFEval (0-Shot) (strict accuracy)
78.25Text Generation · 0-shot
BBH (3-Shot) (normalized accuracy)
56.27Text Generation · 3-shot
MATH Lvl 5 (4-Shot) (exact match)
35.35Text Generation · 4-shot
GPQA (0-shot) (acc_norm)
14.88Text Generation · 0-shot
MuSR (0-shot) (acc_norm)
15.18Text Generation · 0-shot
MMLU-PRO (5-shot) (main; test; accuracy)
46.56Text Generation · 5-shot
n-shot
3Overall: · bbh · get-answer · exact_match
Value
0.824Overall: · bbh · get-answer · exact_match
Every reported result27
Stderr
0.004Overall: · bbh · get-answer · exact_match
Pass@1
0.336LiveCodeBench
Easy Pass@1
0.729LiveCodeBench
Medium Pass@1
0.163LiveCodeBench
Hard Pass@1
0.000LiveCodeBench
Score
48.0Arena-Hard
Average Tokens
628Arena-Hard
Turn
1MT-Bench
Score
9.056MT-Bench
Turn
2MT-Bench
Score
8.675MT-Bench
Score
8.866MT-Bench
Avg.
41.08Open LLM Leaderboard Evaluation Results
IFEval (0-Shot)
78.25Open LLM Leaderboard Evaluation Results · 0-shot
BBH (3-Shot)
56.27Open LLM Leaderboard Evaluation Results · 3-shot
MATH Lvl 5 (4-Shot)
35.35Open LLM Leaderboard Evaluation Results · 4-shot
GPQA (0-shot)
14.88Open LLM Leaderboard Evaluation Results · 0-shot
MuSR (0-shot)
15.18Open LLM Leaderboard Evaluation Results · 0-shot
MMLU-PRO (5-shot)
46.56Open LLM Leaderboard Evaluation Results · 5-shot

Values as printed on the card, with the publisher's own settings (card section: Evaluation Results › Big-Bench Hard (BBH) › Overall:; Evaluation Results › LiveCodeBench); column “Smaug-Qwen2-72B-Instruct”. Not comparable across publishers and not used in any ranking. Model card

Runs on

Fast memory holds it 17

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

Show all 17

Within memory, outside the fast part 6

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 6

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.

Task
text-generation
Architecture
Qwen2ForCausalLM
Library in source
transformers
Weight license
Publisher terms: tongyi-qianwen
Commercial use
Allowed with conditions Products with over 100M monthly users need an Alibaba Cloud license · Tongyi Qianwen license (Qwen/Qwen2-72B-Instruct LICENSE; other versions carry the same commercial condition) · read 2026-10-18license text
Every stored field13 fields
Revision checked
df3d9a1ef66522e14692809086113211a09b36db
Architecture
Qwen2ForCausalLM
Library
transformers
Hub task tag
text-generation
Formats
safetensors
Access
Open download
Publisher kind
Official
Tensor evidence
floating-tensor-elements · 72.71B · BF16checked 2026-09-26
Repository created
2024-06-26creation is not the model's release
Repository updated
2024-08-06a commit is not a release date
Hub downloads (30 days) · likes
98 · 10this repository only · read 2026-10-25
Read from the Hub page
transformers class, task tags, license nameHub overview and file listing · read 2026-10-18
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.