Unsloth loader can run Python even with trust disabled
CVE-2026-93348, scored 8.6, is fixed in Unsloth 2026.8.20 and Unsloth Zoo 2026.8.14.
Stories per day · 30 days
3 RSS
Relatedcode-execution1coding-agents1flint1gguf1hugging-face1mixture-of-experts1model-loading1quantization1supply-chain1
14 stories, newest first · one card per story
Stories tagged #unsloth
Unsloth lists GGUF builds of Recursive's Flint coding model
Flint is a 39.8B MoE model with about 2.5B active parameters, scored by Recursive at 54.9% on Terminal-Bench 2.1.
What Happens When a Trusted Model Repo Changes? Unsloth Studio Re-Checks Before It Runs
Unsloth Studio re-checks model code, weights, packages, and tools before running a changed trusted repo.
unsloth/embeddinggemma-2-GGUF — new model trending #29 on Hugging Face
Unsloth released GGUF weights for Google DeepMind's EmbeddingGemma 2, a 740M multimodal embedding model.
2
Unsloth’s model picker had a code-execution problem
Unsloth Studio executed remote Python when users merely selected a model, letting crafted repos run code on developer machines.
4
Unsloth Studio RCE Flaw Lets Malicious Hugging Face Models Execute Code
Patched Unsloth Studio flaw let malicious Hugging Face models execute Python code when selected, running with user privileges; users must upgrade to 2026.6.9.
2
Unsloth Fixes Arbitrary Code Execution Flaw Triggered by Malicious Hugging Face Models
Unsloth patched Studio 2026.6.9 after default remote-code trust let malicious Hugging Face models execute Python on inspection.
4
Unsloth Studio Flaw Turns Routine Model Inspection Into Code Execution
Patched Unsloth Studio flaw let malicious AI models run arbitrary Python code on researchers' machines via trust_remote_code during model inspection.
unsloth/Qwen-Image-2.1-GGUF — new model trending #30 on Hugging Face
Unsloth published GGUF quantized versions of Qwen-Image-2.1, Alibaba's 7B text-to-image and editing model, using Dynamic 2.0 per-layer precision.
11
DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUF — new model trending #30 on Hugging Face
DavidAU releases Qwen3.8-27B-TWIN-TURBO, an uncensored GGUF fine-tune claiming sharply reduced thinking tokens and self-reported benchmark gains.
6
Benchmarking Qwen3.8 27B quantizations: 4-bit holds up, 1-bit collapses
Quesma benchmarks Qwen3.8 27B quantizations: 4-bit Q4_K_M matches BF16 on key benchmarks while 1-bit collapses to random chance.
10
Jackrong/Qwopus3.8-27B-Flash-GGUF — new model trending #26 on Hugging Face
Community fine-tune Qwopus3.8-27B-Flash, built on Qwen3.8-27B, cuts agent reasoning latency with 12.8% faster decoding and 80.7% MTP acceptance.
10
DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF — new model trending #8 on Hugging Face
A new Qwen3.8-27B GGUF fine-tune claims ARC-C 735 at 8-bit with thinking tokens cut 2x-10x versus the base model.
unsloth/Qwen3.8-Flash-Next-GGUF — new model trending #21 on Hugging Face
Qwen released Qwen3.8-Flash-Next, an experimental 125B-parameter open-weight MoE previewing the Qwen4 architecture, with Unsloth shipping optimized GGUF quants.
6