Smaug Flash
Abacus AI · abacusai/Smaug-Flash
Weights license: MIT · code and components may use other terms
Quality
Quality · Overall
LiveBench 2026-06-25 · 0–100 · higher is better · this model outlined, #6 of 22
- Color = publisher
- Memory under review
Source: LiveBench 2026-06-25 · collected 2026-09-26 · open models without a score are not drawn (no score ≠ 0)
No result in LMArena 2026-10-22 Not in LMArena 2026-10-22
LiveBench categories
This model's mean per category · 0–100
Source: LiveBench 2026-06-25 · collected 2026-09-26 · open models without a score are not drawn (no score ≠ 0)
Reported by the publisher
Quality × memory
Not placed on quality × memory
There is no validated Q4 planning estimate for this checkpoint (its parameter basis does not allow one).
Runs on
No memory requirement to match
Without a parameter count with a known basis or a documented memory path, no hardware is grouped. Nothing is guessed.
Smaug Flash is a text model from Abacus AI; this catalog has no verified parameter count for it, so no memory is estimated. It was released on September 10, 2026 and reads up to 1,048,576 tokens of context. No GGUF or MLX file for it was collected from the Hub, so this page lists no file sizes or run commands. It scores 77.4 overall in LiveBench 2026-06-25.
Compare Smaug Flash using its publisher card and the LiveBench 2026-06-25 snapshot. This is quality evidence, not local speed.
This profile has no simplified memory estimate because the available size evidence is incomplete or includes separate components. Check the exact checkpoint, format and runtime before planning hardware.
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
No validated memory estimate for this model and runtime.
Q4 planning estimate only. Check checkpoint format, runtime support, KV cache, context, batch size and offload before choosing hardware.
Documented ways to run it
Copied as printed in the linked source (read 2026-10-18); not run by this site.
vllm serve abacusai/Smaug-Flash \
--trust-remote-code --kv-cache-dtype fp8 --block-size 256 \
--data-parallel-size 4 --enable-expert-parallel \
--moe-backend deep_gemm_mega_moe \
--attention-config '{"use_fp4_indexer_cache": true}' \
--speculative-config '{"method":"dspark","num_speculative_tokens":7,"draft_sample_method":"greedy"}'sglang serve \
--trust-remote-code \
--model-path abacusai/Smaug-Flash \
--tp 4 \
--enable-dp-attention \
--moe-runner-backend flashinfer_mxfp4 \
--speculative-algorithm DSPARK \
--mem-fraction-static 0.90 \
--chunked-prefill-size 4096 \
--swa-full-tokens-ratio 0.1Evidence level: Generic estimate only; no execution reproduced by this site.
- Versions to download
- — No GGUF or MLX file collected from the Hub for this checkpoint
- Publisher sampling defaults
- — No Hub file facts collected for this checkpoint
- Chat template markers
- — Chat template not read for this checkpoint
Before downloading
- Check the exact checkpoint and license linked here.
- Confirm a compatible runtime and precision or quantization for your platform.
- Allow for context, batch size and any extra media components beyond the weights.
Technical details
What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.
- Checkpoint / version
- abacusai/Smaug-Flash
- Task and modality
- language and reasoning · text
- Count and basis
- Not verified
- Context
- 1,048,576 tokens published for this modelabacusai/Smaug-Flash model card (Hugging Face) · read 2026-10-09source
- Architecture
- MoEabacusai/Smaug-Flash model card (Hugging Face) · read 2026-10-09source
- Released
- Abacus.AI Launches the Smaug Line of Open-Weight Models Optimized for Enterprise Agentic AI Use Cases (PR Newswire, dateline Sept. 10, 2026) · read 2026-10-10source
- Runtime and precision
- No local execution verified.
- Commercial use
- Allowed MIT license text (SPDX) · read 2026-10-18license text
Every stored field
- Revision checked
- fa82a6411805742e3b755c93fceb2e672c0989ba
- Architecture
- DeepseekV4ForCausalLM
- Library
- transformers
- Hub task tag
- text-generation
- Declared base models
- deepseek-ai/DeepSeek-V4-Flash-0731
- Formats
- safetensors
- Access
- Open download
- Publisher kind
- Official
- Repository created
- 2026-08-29creation is not the model's release
- Repository updated
- 2026-09-10a commit is not a release date
- Hub downloads (30 days) · likes
- 453 · 21this 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.
- Publisher checkpoint and model card
- Weight license and use terms
- Quality benchmark source · LiveBench 2026-06-25 overall
Catalog reviewed: 2026-09-30. Benchmark release: 2026-06-25; snapshot collected: 2026-09-26.