Run #LLMs# on @NVIDIARobotics #Jetson# without x86 ONNX export. 🚀 #TensorRT-Model-Connect# on reComputer Classic J5012 (#AGXOrin# 64GB, #JP7#.2). @huggingface checkpoint → trtmc build → .bundle on device trtmc run for text gen Tested: #Qwen3-4B# FP16 (~41GB container peak, 64GB recommended) No ONNX hop. Edge LLM/agent ready. Would you use on-device TRTMC for prototyping, or keep ONNX export for production? 👇 Full guide: Get your own one: #NVIDIA# #Jetson# #TensorRT# #TRTMC# #AGXOrin# #EdgeAI# #LLM# #PhysicalAI# #SeeedStudio#

How did I miss this?! Bonsai isn’t just an LLM family. Back in May, PrismML released Bonsai Image 4B, a crazy low-bit version of FLUX.2 Klein 4B designed to run locally on 🍎 iPhones. Look at this 🎨 FLUX.2 Klein 4B transformer 💾 FP16: 7.75GB 🌳 Ternary Bonsai: 1.21GB And the entire Apple deployment payload, including its compressed text encoder + VAE, is only: 🔥 3.88GB 📱 iPhone 17 Pro Max 🧠 A19 Pro / 12GB unified memory 🖼️ 512×512 ⚡ 9.4 sec/image 📲 MLX Swift ☁️ No cloud 💾 Bomsai Studio (App Store) M4 Pro: ~5.8 sec/image. No cloud. The ~4B diffusion transformer is paired with a 4-bit Qwen3-4B text encoder, which gets unloaded after the prompt is encoded to save memory. And there’s also 🍎 Mac / iPhone / iPad support 🟢 low-bit Gemlite builds for Nvidia GPUs 🔓 Apache 2.0 This is completely separate from the Bonsai 2 27B LLM I’ve been posting about. PrismML took a 7.75GB FLUX transformer and crunched it down to 1.21G and put image generation on an iPhone. 👀 And somehow I missed this for 4 months.

⚡ DSpark vs DFlash: Up to 2.55× Throughput in a vLLM Test With DSpark checkpoints and vLLM support now available, parallel speculative decoding is becoming a practical serving option rather than just a research idea. Zhihu contributor kaiyuan explains how DFlash and DSpark work, then benchmarks both on the same Qwen3-4B target model. The result: DSpark reached 2.45–2.55× baseline throughput, while DFlash achieved 1.96–2.09×. 1️⃣ Why LLM Decoding Is Naturally Slow Autoregressive models generate text one token at a time. Token n+1 cannot be produced before token n. This sequential dependency limits how much parallel GPU compute can be used during decoding. Non-autoregressive generation works differently. It treats generation more like filling multiple blanks and can predict several positions in one forward pass. Parallel speculative decoding combines both ideas: 🔹 A lightweight draft model proposes several tokens in parallel. 🔹 The target model verifies them in one batch. 🔹 Accepted tokens are kept; generation restarts from the first rejection. The challenge is making the draft both fast and accurate enough to be useful. 2️⃣ Why Traditional Draft Models Hit a Wall Conventional speculative decoding often uses a smaller autoregressive model such as EAGLE. It produces higher-quality drafts, but still generates candidate tokens sequentially. Longer drafts require more draft-model forward passes. Making the draft model larger improves accuracy but also increases latency. Parallel drafters solve the latency problem by proposing an entire token block at once. However, later tokens in that block do not fully depend on earlier predictions. Their accuracy often drops quickly, creating suffix acceptance decay. 3️⃣ How DFlash Improves Parallel Drafting DFlash uses a parallel, fill-in-the-blanks-style draft model. To improve draft quality, it extracts hidden states from several layers of the target model and fuses them into an additional context representation. Each draft layer then attends to two sources: 🔹 Context derived from the target model 🔹 Representations from the draft tokens themselves The target model’s hidden states make the lightweight drafter more informed without requiring multiple autoregressive passes. DFlash can therefore propose a long block in one forward pass. But longer blocks still create a problem: the suffix is more likely to be rejected, while the target model must spend compute verifying it. 4️⃣ DSpark Adds Sequential Structure DSpark extends DFlash with semi-autoregressive generation. It first uses a parallel backbone to generate intermediate logits for multiple positions. A lightweight sequential module, implemented with an RNN or Markov head, then produces the draft tokens from left to right. This small sequential step restores dependencies inside the block without giving up most of the parallel speed. It also predicts a confidence value for every token: the probability that the token will survive target-model verification if the previous prefix is accepted. The result is a stronger draft with less suffix decay. 5️⃣ Verification Length Becomes Dynamic DSpark does not automatically send the entire draft to the target model. Its Hardware-Aware Prefix Scheduler considers: 🔹 The survival probability of each draft prefix 🔹 The current batch size and system load 🔹 A profiled steps-per-second curve for the hardware Verifying one more token may increase the expected accepted length. But it also enlarges the verification batch and can reduce processing speed. The scheduler expands each prefix only while estimated throughput continues improving. Low-confidence suffix tokens are discarded before they consume target-model compute. Draft long, but verify only the prefix that is still worth verifying. 6️⃣ The vLLM Test Setup The author tested both methods under the same environment: 🔹 8× NVIDIA A800-SXM4-80GB 🔹 Qwen3-4B target model 🔹 DSpark block-7 and DFlash block-16 draft models 🔹 vLLM 0.26.0 The initial comparison used DSpark with four speculative tokens and DFlash with seven. On 250 GSM8K questions: ✅ DSpark: 35.2% accuracy, 0.75s average latency ✅ DFlash: 31.6% accuracy, 0.84s average latency On 250 MMLU questions: ✅ DSpark: 28.8% accuracy, 0.24s average latency ✅ DFlash: 27.6% accuracy, 0.27s average latency DSpark reduced average latency by roughly 11% in both tests. 7️⃣ Throughput Is the Stronger Result Because the two methods used different speculative-token settings, the author swapped those parameters and tested again. 🔹 Original settings: DSpark=7, DFlash=4 DSpark reached 584 tok/s, while DFlash reached 449 tok/s. ✅ DSpark was 1.30× faster. 🔹 Swapped settings: DSpark=4, DFlash=7 DSpark reached 561 tok/s, while DFlash reached 480 tok/s. ✅ DSpark remained 1.17× faster. Changing num_speculative_tokens affected throughput by less than 7%. DSpark remained faster in both configurations, showing that its advantage did not come from receiving a more favorable draft length. Compared with the 229 tok/s baseline: 🔹 DSpark delivered 2.45–2.55× throughput. 🔹 DFlash delivered 1.96–2.09× throughput. At matched settings, DSpark stayed roughly 20% faster than DFlash. ⚠️ Do Not Overread the Accuracy Numbers The accuracy differences are less conclusive. MMLU results varied by about one percentage point. On GSM8K, even the baseline changed from 29.2% to 34.4% across two runs. The author attributes this to different vLLM batch compositions changing floating-point accumulation order. That can alter a small number of token choices even with temperature=0. So the test strongly supports a throughput advantage. It does not establish that speculative decoding improves model intelligence. 💡 The Practical Takeaway DFlash proves that parallel drafting can generate many candidates cheaply. DSpark adds the two components needed for production serving: 🔹 Lightweight sequential modeling to improve draft quality 🔹 Load-aware scheduling to avoid unnecessary verification Its real contribution is not simply drafting more tokens. It is deciding which tokens are still worth verifying under the current serving load. 🔗 DeepSpec: 🔗 Test notebook: 🔗 Full Reading: #DSpark# #DFlash# #SpeculativeDecoding# #vLLM# #LLMInference# #AIInfrastructure# #DeepSeek#

// The agent is its own best speculator // Agents spend a large share of wall-clock time waiting on tool results. Speculation hides that latency by predicting and pre-executing the next call, but external draft models and cached traces are modeling a different policy, so they miss too often to help. New research from UC Santa Barbara and LinkedIn unifies both roles in one model. It runs in agent mode to solve the task and in speculator mode to predict its next tool call from a partial trajectory, fully reusing the prefix KV cache. Joint agent-speculator reinforcement learning derives speculation targets from the agent's own rollouts and alternates updates between the two modes, which keeps dual-mode training from degrading task success. Next tool-call Hit@1 rises from 44.1 to 61.2 for Qwen3-4B and from 48.9 to 66.3 for Qwen3.5-4B, with agent task success preserved. Paper: Learn to build effective AI agents in our academy:

1d 13h 20m, 3,596,831 tokens. Goal achieved? Not quite. It was a hard problem. The agent tried its best and went through 20 full model/eval rounds. In the end, the agent talked itself out of the original contract and declared the goal achieved. I probably would have stopped it anyway, since I could also see from the sidecar that it was struggling. Still, it was a good experiment. My 14" MacBook Pro held up well under a sustained run, with no throttling or heating issue. Qwen3.6 35B A3B OptiQ 4-bit running locally on MLX also held up well. It generated thousands of training data samples, averaging around 50 tps with reasonably good quality. Very impressive. DeepSeek 4 Pro was a good teacher for the training, though there are still areas for improvement. The end result: we LoRAed an expert model, Qwen3-4B-Instruct-2507 + MLX LoRA. We produced a compact 56 MB LoRA adapter on a 4B Qwen base that reaches ~59% three-way decision agreement on the original eval slice, ~91% violation recall, and ~98% valid JSON, but with a high false-positive rate. It is deployable, but probably not quite usable yet. Still, it gives me a clear direction for where to go next. I’ll write more about the whole process later. Stay tuned.

Qwen3.5-4B running CPU-ONLY at up to ~11+ tps on a Ryzen 5 laptop. No GPU. Running models in RAM and CPU is something the Qwen4 team is already thinking about. 💡 I built this standalone .exe because businesses are already deploying local models to save money and ensure privacy. (thumb drive friendly - just drag drop and doubleclick) My llama.cpp recipe 👉 🧠 Qwen3.5-4B Q4_K_M GGUF ⚙️ Ryzen 5 7540U — 6C/12T 🧵 --threads 9 🧵 --threads-batch 12 ⚡ --prio 2 🔄 --poll 50 📦 --batch-size 2048 📦 --ubatch-size 512 🚀 --flash-attn on 🧠 KV cache: q4_0 / q4_0 🔧 --repack 💾 --mmap 👤 --parallel 1 🚫 --device none 🚫 --gpu-layers 0 🚫 KV/op GPU offload 🚫 MTP OFF Interesting result 👉 MTP=3 was slower (~10 tps in benchmarks). Plain decode + 9 threads + Q4 KV hit ~11.4 tok/s. That's about 10% faster just from tuning llama.cpp — on a basic laptop CPU.

ThumbLLM v0.1 Qwen3.5-4B CPU. Windows. Double-click. On my Strix Halo (CPU only, no iGPU offload), it sits near ~20 tok/s. Same recipe idea as the 7540U laptop post: --device none, GGUF Q4_K_M, chat + local API. Missing weights download. Unsigned. SmartScreen will complain. Hash is on the Release. Then run anyway. 🔗 GH /TeksEdge/ThumbLLM/releases/tag/thumbllm-qwen3.5-4b-mtp-q4_k_m-cpu-win-x64-v0.1.0

📰 A 1.56GB local model just took the #1# spot for open models under 4B on Artificial Analysis. Let's run it on ThumbLLM. OpenBMB released MiniCPM5-2B TODAY. Stats 👇 🧠 2.52B dense parameters 💾 Q4_K_M GGUF: just 1.56GB 📚 131K native context ⚖️ Apache 2.0 🦙 llama.cpp 🟢 Ollama 🖥️ LM Studio 🍎 MLX 🤖 Native tool calling + agent training Artificial Analysis Intelligence Index v4.2 ... 🥇 MiniCPM5-2B → 15 Qwen3.5-4B Reasoning → 14* Qwen3.5-9B Reasoning → 15* Granite 4.2 3B → 11 *Qwen scores are estimated by Artificial Analysis. So a 1.56GB Q4 GGUF is landing in the same AA Intelligence Index tier as Qwen3.5-9B. 🤖 GDPval-AA v2 Elo → 831 🏦 τ³-Banking → 21% ⚡ 19K output tokens/task vs 56K for Ling 3.0 Tiny OpenBMB even released the training data and an official DSpark speculative decoding model. No trustworthy local tok/s numbers yet. That is the benchmark I want next. 🔥 Let's run it on ThumbLLM! 🔗 HF /openbmb/MiniCPM5-2B

Excited to share our latest research introducing Qwen-VLA—a unified Vision-Language-Action model for general embodied intelligence 🤖 By combining Qwen3.5-4B with a 1.15B DiT decoder, it unifies manipulation, navigation, and trajectory prediction into a single framework. With embodiment-aware prompts, the same Qwen-VLA model can operate across 11 robot embodiments under a unified architecture—covering single-arm, dual-arm, and humanoid platforms without task-specific policy heads—without task-specific architecture forks or separate policy heads.