savoji/qwen3.5-0.8b-tablevqa-lora
Updated ⢠31
Sajjad Pakdamansavoji
savoji
AI & ML interests
VLM, VLA, LLM, Robotics, Computer Vision
Recent Activity
repliedto their post about 3 hours ago
A 284B-parameter DeepSeek-V4-Flash now runs on a 64 GB desktop with 0 GPUs: llama-modchip shrinks the checkpoint to 56.56 GiB (1.71 bpw) and decodes at 9.1 to 14.7 tok/s.
The standard UD-IQ1_S build is 76.87 GiB, above the ~62.5 GiB usable on a 64 GB Linux box. The repo mixes precisions (routed experts mostly IQ1_S, MLA projections in a custom Fractal-64 type) and patches the CPU kernels. The model plus a 256K KV cache then sits at 57.61 to 58.9 GiB RSS with zero swap. The repo was created on 2026-10-29 and already has 744 stars and 470 points on Hacker News.
đ The numbers
⢠Size: 56.56 GiB, 20.31 GiB smaller than UD-IQ1_S
⢠Prefill: 25.0 to 44.36 tok/s (+77%) on a 16-core Ryzen 9 9955HX
⢠Decode: 5.91 tok/s unpatched, 9.06 to 9.95 tok/s at Top-6, 11.5 to 14.7 tok/s with the n-gram drafter
â ď¸ Caveats
⢠"Lossless" means bit-exact against the same re-quantized checkpoint. Versus UD-IQ1_S the author reports 0.9964 top-logit cosine similarity
⢠The 98.5/100 quality score comes from the author's own gate, and the headline speeds come from one machine
⢠The custom tensor type 40 is rejected by stock llama.cpp, Ollama and LM Studio
đ ď¸ Try it
⢠Run scripts/check_cpu_readiness.py from the repo: it needs no model download
⢠Run ./modchip bench for speed, then ./modchip eval to check the quality claims yourself
Repo:
https://github.com/synchopate/llama-modchip
HN thread:
https://news.ycombinator.com/item?id=50411961
Would you accept a custom runtime for 9 to 15 tok/s from a 284B model on a 64 GB box?
đ Read it elsewhere
⢠The deep dive on Medium: https://medium.com/p/e47ab3581f58
⢠The long read on Substack: https://sajjadpakdamansavoji.substack.com/p/llama-modchip-runs-a-284b-deepseek
⢠The thread on X: https://x.com/saavoji/status/2119858773280141526
⢠Every version on sajjadpsavoji.github.io: https://sajjadpsavoji.github.io/blog#llama-modchip posted an update about 10 hours ago
One frozen encoder now maps 3 tactile sensor types (piezoresistive, magnetic, visuotactile) into the same token space, and the Tiny checkpoint runs on CPU.
LingBot-Touch bets that touch progresses by standardizing the representation, not by building a better sensor. A JEPA-style model uses modality-specific tokenizers and one shared Transformer, predicting masked tactile content in latent space. The authors say the tokens plug into diffusion policy and VLAs such as pi0.5 and LingBot-VLA. The paper has 91 upvotes on HF Daily Papers.
đ What's released
⢠Frozen target encoder plus utilities that output tokens [B,N,C] with time, finger and position addresses
⢠Tiny and Small checkpoints, Apache-2.0, with 120 sample files for Sharpa and XHand
⢠Inference only: pretraining code and policy integrations are not described as released
đ ď¸ Try it
⢠Run infer.py on the Sharpa or XHand sample with --device cpu
⢠Read out with cross-attention queries, not mean/max pooling: each token mixes information from other taxels and time steps
â ď¸ Caveats
⢠A new raw taxel layout needs verified geometry calibration; matching tensor shapes is not enough
⢠The abstract gives no per-task numbers, so check the paper's tables before trusting the gains
⢠Model files need an account with access to the model repo
https://huggingface.co/papers/2611.12806
https://github.com/Robbyant/lingbot-touch
Would you put a frozen cross-sensor tactile encoder in front of your policy, or keep per-sensor pipelines?
đ Read it elsewhere
⢠The deep dive on Medium: https://medium.com/p/0d2028d8fc73
⢠The long read on Substack: https://sajjadpakdamansavoji.substack.com/p/lingbot-touch-argues-touch-needs
⢠The thread on X: https://x.com/saavoji/status/2120209644392194083
⢠Every version on sajjadpsavoji.github.io: https://sajjadpsavoji.github.io/blog#lingbot-touch upvoted a paper 1 day ago
Fragility Is Not Reducible to Hardness: Conditional Causal Difficulty for LLMsOrganizations
None yet