P

prismml

prismml (@prismml on X) shares product and developer updates on image-generation models optimized for local/on-device inference, bug fixes, and engineering notes relevant to mobile and PC silicon, NPUs, and quantization-aware deployment.

Trust score
0 / 100
Track record
0 / 100
Thesis calls
46
Evaluated calls
46
Average return
+21.36%
Win rate
80%

Past bets that played out

Key calls center on the release of 1-bit and Ternary Bonsai Image 4B — diffusion models engineered for high-quality local inference on laptops and phones — and the implications for edge AI, quantization, and device-level acceleration.

MUrightbacktest HOLD

Post highlights strong performance of a local AI model (“Bonsai” by PrismML) running agentically on a consumer GPU (RTX 4070 Super), framing 2026 as a strong year for “Local AI.” It also suggests “intelligence density” as a coming benchmark driven by memory shortages, implying continued demand for efficient models, GPUs, and memory bandwidth/capacity.

Mentioned: Jul 17, 2026, 1:41 PM EDTConviction: 52 / 100Return: +119.85%Observed price: $848.95
Source: Thomas Konings @tkon99 3h Finally had the time to test Bonsai by @PrismML out. On my mere RTX 4070 Super I get 45 t/s...
MUrightbacktest HOLD

PrismML claims it is launching “Bonsai 27B,” a 27B-parameter multimodal model (based on Qwen3.6 27B) that can run on a phone, and a user reports minimal quality loss from a 1-bit version. If true/replicable, this supports the market narrative that aggressive quantization and model optimization will push more AI inference on-device (handsets/edge) rather than in the cloud.

Mentioned: Jul 15, 2026, 5:14 AM EDTConviction: 52 / 100Return: +106.13%
Source: Aj @illetrateNerd 49m I tested the 1bit one given my resources and there has only been a minimal intelligence loss. I...
MUrightbacktest HOLD

PrismML claims it is releasing “Bonsai 27B,” described as the first ~27B-parameter-class multimodal model capable of running on a phone, enabling higher-tier on-device/local AI (reasoning, tool use, long context). If credible and broadly adopted, this supports a market thesis that more AI inference will shift to edge devices, benefitting mobile SoC/IP and foundry supply chains; it is modestly negative for pure cloud-inference dependency at the margin but likely complementary near-term.

Mentioned: Jul 14, 2026, 1:36 PM EDTConviction: 50 / 100Return: +104.62%Observed price: $983.12
Source: Pinned PrismML @PrismML 4h Today, we’re announcing Bonsai 27B: the first 27B-class model to run on a phone. Bonsai 27...

What this channel is watching now

Top tickers mentioned: AAPL (2 mentions, avg conviction 0.37), QCOM (1 mention, avg conviction 0.56), AMD (1 mention, avg conviction 0.47), INTC (1 mention, avg conviction 0.45), MSFT (1 mention, avg conviction 0.28). Coverage is driven by edge/on-device AI releases and developer-oriented product updates rather than direct buy/sell recommendations.

Latest videos and market context

Recent posts are short product or community items: a pinned release announcement for Bonsai Image 4B, a local-demo bug-fix repost, and a generic invitation link. No long-form market videos were posted in the sample.

PrismML @PrismML 4m 🦞🦞🦞 Vincent Koc @vincent_koc 3h ♥️Huge thanks to @nvidia for the DGX Sparks for @openclaw enginee...

Jul 23, 2026, 11:54 PM EDT

Social post thanking NVIDIA for providing DGX Spark systems to PrismML/OpenClaw engineering; hints at upcoming joint product announcements to improve local model experience and enable more local AI use-cases.

Glenn Sonna @GlennSonna 7h Bonsai-1.7B from @PrismML: a 1-bit model decoding at 32 tok/s on a OnePlus 13. Q1_0. 237 M...

Jul 23, 2026, 3:41 PM EDT

Post claims a 1-bit quantized 1.7B-parameter model (“Bonsai-1.7B”) runs at ~32 tokens/s on a OnePlus 13 using CPU-only (no GPU), implying meaningful on-device AI capability via extreme quantization.

Omead Pooladzandi @HessianFree 2h Replying to @PrismML and @togethercompute Bonsai 27b goes brrr 1 1 1 1 4 4 284 2 8 4

Jul 21, 2026, 3:10 PM EDT

Very low-information social post referencing “Bonsai 27b” (likely an AI model) with no concrete news, metrics, company names, or catalysts. Not actionable for public-market trading.

PrismML @PrismML Jul 21 Try Ternary Bonsai 27B directly on Hugging Face , powered by @togethercompute huggingface.co/...

Jul 21, 2026, 3:00 PM EDT

PrismML is promoting a demo of its “Ternary Bonsai 27B” model on Hugging Face, powered by Together Compute. This is a product/visibility update in the open-source/hosted AI inference ecosystem, but it contains no financial metrics, customer adoption data, or explicit commercial implications for public companies.

Proof-backed call history

Performance snapshot: 6 recommendations evaluated, average return 25.9467%, win rate 83.33%. Total published recommendations in this dataset: 6.

NVDArightbacktest DEMOTE

Post claims a 1-bit quantized 1.7B-parameter model (“Bonsai-1.7B”) runs at ~32 tokens/s on a OnePlus 13 using CPU-only (no GPU), implying meaningful on-device AI capability via extreme quantization.

Mentioned: Jul 23, 2026, 3:41 PM EDTConviction: 24 / 100Return: -17.10%Observed price: $208.76
Source: Glenn Sonna @GlennSonna 7h Bonsai-1.7B from @PrismML: a 1-bit model decoding at 32 tok/s on a OnePlus 13. Q1_0. 237 M...
ARMwrongbacktest DEMOTE

Post claims a 1-bit quantized 1.7B-parameter model (“Bonsai-1.7B”) runs at ~32 tokens/s on a OnePlus 13 using CPU-only (no GPU), implying meaningful on-device AI capability via extreme quantization.

Mentioned: Jul 23, 2026, 3:41 PM EDTConviction: 40 / 100Return: -5.99%Observed price: $283.04
Source: Glenn Sonna @GlennSonna 7h Bonsai-1.7B from @PrismML: a 1-bit model decoding at 32 tok/s on a OnePlus 13. Q1_0. 237 M...
QCOMrightbacktest HOLD

Post claims a 1-bit quantized 1.7B-parameter model (“Bonsai-1.7B”) runs at ~32 tokens/s on a OnePlus 13 using CPU-only (no GPU), implying meaningful on-device AI capability via extreme quantization.

Mentioned: Jul 23, 2026, 3:41 PM EDTConviction: 46 / 100Return: +50.12%Observed price: $171.11
Source: Glenn Sonna @GlennSonna 7h Bonsai-1.7B from @PrismML: a 1-bit model decoding at 32 tok/s on a OnePlus 13. Q1_0. 237 M...
GOOGLrightbacktest HOLD

Social post praising an AI model/agent setup (“Bonsai 27b” / “bonsai 3.9gb model”) that performs tool-calls reliably in a local Hermes agent workflow. No explicit company, product vendor, revenue impact, or catalyst mentioned.

Mentioned: Jul 19, 2026, 12:14 PM EDTConviction: 17 / 100Return: +20.15%
Source: Omead Pooladzandi @HessianFree 13h Love to see people working with Bonsai 27b Sudo su @sudoingX 19h watch bonsai 3.9g...
AMZNrightbacktest HOLD

Social post praising an AI model/agent setup (“Bonsai 27b” / “bonsai 3.9gb model”) that performs tool-calls reliably in a local Hermes agent workflow. No explicit company, product vendor, revenue impact, or catalyst mentioned.

Mentioned: Jul 19, 2026, 12:14 PM EDTConviction: 17 / 100Return: +21.77%
Source: Omead Pooladzandi @HessianFree 13h Love to see people working with Bonsai 27b Sudo su @sudoingX 19h watch bonsai 3.9g...
MSFTrightbacktest DEMOTE

Social post praising an AI model/agent setup (“Bonsai 27b” / “bonsai 3.9gb model”) that performs tool-calls reliably in a local Hermes agent workflow. No explicit company, product vendor, revenue impact, or catalyst mentioned.

Mentioned: Jul 19, 2026, 12:14 PM EDTConviction: 18 / 100Return: +6.88%
Source: Omead Pooladzandi @HessianFree 13h Love to see people working with Bonsai 27b Sudo su @sudoingX 19h watch bonsai 3.9g...
NVDArightbacktest HOLD

Social post praising an AI model/agent setup (“Bonsai 27b” / “bonsai 3.9gb model”) that performs tool-calls reliably in a local Hermes agent workflow. No explicit company, product vendor, revenue impact, or catalyst mentioned.

Mentioned: Jul 19, 2026, 12:14 PM EDTConviction: 28 / 100Return: +11.88%
Source: Omead Pooladzandi @HessianFree 13h Love to see people working with Bonsai 27b Sudo su @sudoingX 19h watch bonsai 3.9g...
MSFTrightbacktest DEMOTE

Post highlights strong performance of a local AI model (“Bonsai” by PrismML) running agentically on a consumer GPU (RTX 4070 Super), framing 2026 as a strong year for “Local AI.” It also suggests “intelligence density” as a coming benchmark driven by memory shortages, implying continued demand for efficient models, GPUs, and memory bandwidth/capacity.

Mentioned: Jul 17, 2026, 1:41 PM EDTConviction: 35 / 100Return: -0.04%Observed price: $393.82
Source: Thomas Konings @tkon99 3h Finally had the time to test Bonsai by @PrismML out. On my mere RTX 4070 Super I get 45 t/s...
QCOMwrongbacktest DEMOTE

Post highlights strong performance of a local AI model (“Bonsai” by PrismML) running agentically on a consumer GPU (RTX 4070 Super), framing 2026 as a strong year for “Local AI.” It also suggests “intelligence density” as a coming benchmark driven by memory shortages, implying continued demand for efficient models, GPUs, and memory bandwidth/capacity.

Mentioned: Jul 17, 2026, 1:41 PM EDTConviction: 50 / 100Return: -23.49%Observed price: $171.78
Source: Thomas Konings @tkon99 3h Finally had the time to test Bonsai by @PrismML out. On my mere RTX 4070 Super I get 45 t/s...
MUrightbacktest HOLD

Post highlights strong performance of a local AI model (“Bonsai” by PrismML) running agentically on a consumer GPU (RTX 4070 Super), framing 2026 as a strong year for “Local AI.” It also suggests “intelligence density” as a coming benchmark driven by memory shortages, implying continued demand for efficient models, GPUs, and memory bandwidth/capacity.

Mentioned: Jul 17, 2026, 1:41 PM EDTConviction: 52 / 100Return: +119.85%Observed price: $848.95
Source: Thomas Konings @tkon99 3h Finally had the time to test Bonsai by @PrismML out. On my mere RTX 4070 Super I get 45 t/s...
AMDrightbacktest HOLD

Post highlights strong performance of a local AI model (“Bonsai” by PrismML) running agentically on a consumer GPU (RTX 4070 Super), framing 2026 as a strong year for “Local AI.” It also suggests “intelligence density” as a coming benchmark driven by memory shortages, implying continued demand for efficient models, GPUs, and memory bandwidth/capacity.

Mentioned: Jul 17, 2026, 1:41 PM EDTConviction: 50 / 100Return: +46.73%Observed price: $495.76
Source: Thomas Konings @tkon99 3h Finally had the time to test Bonsai by @PrismML out. On my mere RTX 4070 Super I get 45 t/s...
NVDArightbacktest HOLD

Post highlights strong performance of a local AI model (“Bonsai” by PrismML) running agentically on a consumer GPU (RTX 4070 Super), framing 2026 as a strong year for “Local AI.” It also suggests “intelligence density” as a coming benchmark driven by memory shortages, implying continued demand for efficient models, GPUs, and memory bandwidth/capacity.

Mentioned: Jul 17, 2026, 1:41 PM EDTConviction: 55 / 100Return: +8.96%Observed price: $202.81
Source: Thomas Konings @tkon99 3h Finally had the time to test Bonsai by @PrismML out. On my mere RTX 4070 Super I get 45 t/s...

About this channel

prismml posts technical progress, demos, and release notes focused on on-device image generation and quantization techniques. Content is primarily developer- and product-quality updates with secondary implications for hardware and inference economics.

Subscribersn/a
Videosn/a
Win rate80%
Average return+21.36%

@prismml

Unlock the full track record

Follow @prismml on X for engineering releases, local inference demos, and updates on Bonsai Image model development.

34 more thesis calls are available after sign-up.