Model: BotPsy 0.8B QVAC/Tether published BotPsy 0.8B, a Qwen3.5-based text-only model for tool calling and on-device assistant workflows, with 752,393,024 language parameters and a 262K maximum context window. The Hugging Face repository qvac/BotPsy-0.8B-GGUFs ships two GGUF quantizations, Q4_K_M at 0.53 GB (529,296,960 bytes) and Q8_0 at 0.81 GB (811,843,040 bytes), both listed as read on 2026-11-17, and the site's VRAM figures of 0.6 GB and 0.9 GB at 4K context are estimates rather than measurements. Only 6 of the model's 24 layers keep KV caches that grow with context, so extending from 4K to 32K adds about 0.33 GB, while holding the full 256K native window at Q4_K_M would need about 4 GB; no measured speed or perplexity-loss percentage is recorded. BotPsy 0.8B 0.75B QVAC BotPsy QVAC/Tether’s Qwen3.5-based model for tool calling and on-device assistant workflows. The published GGUFs contain 752,393,024 language parameters; the original repository’s larger total includes the vision tower. These files are text-only and ship no projector, so image use is not offered here. Six of 24 layers keep growing KV caches; fixed recurrent state is not separately sized. No measured speed or perplexity-loss percentage is recorded. 262K Max Context 2 Quant Variants GGUF Q8 0 Best Quality — Perplexity rise best build Quantization Variants Per-quant VRAM, quality loss, and inference speed on RTX 4090 Measured = run on this site · Estimated = not run here: calculated, or a figure this site has not verified · Community = public reports | Format | Level | BPW | VRAM | PPL Loss | Speed | Source | Actions | |---|---|---|---|---|---|---|---| | GGUF | Q4 K M | 5.627877379150182 | 0.6 GB | — | — | Estimated | | | GGUF | Q8 0 | 8.632116610374101 | 0.9 GB | — | — | Estimated | | Which file each size is for A file size is not a memory figure: the VRAM column is the calculator's total at 4K context — weights plus KV cache plus a 10% activation buffer. Units differ on purpose: file sizes are decimal GB, as Hugging Face lists them; the VRAM column is GiB 1024³ bytes with 2% added to the weights, so 7.12 GB of file counts as about 6.8 GiB there. A vision projector mmproj , where the repo ships one, is a separate download and is in neither number. - GGUF Q4 K M qvac/BotPsy-0.8B-GGUFs https://huggingface.co/qvac/BotPsy-0.8B-GGUFs · botpsy-0.8b-q4 k m-imat.gguf · 0.53 GB 529,296,960 bytes · listing read 2026-11-17 - GGUF Q8 0 qvac/BotPsy-0.8B-GGUFs https://huggingface.co/qvac/BotPsy-0.8B-GGUFs · botpsy-0.8b-q8 0.gguf · 0.81 GB 811,843,040 bytes · listing read 2026-11-17 Related community runs These runs describe their own settings. Their speeds do not replace this estimate or prove your configuration fits. Our reviewed link index has no run for this model yet. You can browse community reports or share your own test below. Browse more runs on llamaPerf ↗ https://llamaperf.com/ Similar models Compare with Llama 3.2 https://quantized.uk/tools/compare/?a=botpsy-0-8b&b=llama-3.2-3b 3BConsumer GPUMac / Apple SiliconQ4 K M2.5 GB+3.5%perplexity rise https://quantized.uk/quant-hub/llama-3.2-3b/ Llama 3.2 3B Instruct Meta Llama 3.2 Tiny but capable. Runs on 4GB VRAM or 8GB RAM, even on phones via llama.cpp. 3BConsumer GPUMac / Apple SiliconQ4 K M2.1 GB+3.2%perplexity rise https://quantized.uk/quant-hub/qwen2.5-3b/ Qwen2.5 3B Instruct Alibaba Qwen2.5 Tiny Qwen2.5 for edge devices. Runs on 4GB VRAM or Raspberry Pi class hardware. 1BConsumer GPUMac / Apple SiliconQ4 K M0.9 GB+4.2%perplexity rise https://quantized.uk/quant-hub/llama-3.2-1b/ Llama 3.2 1B Instruct Meta Llama 3.2 Ultra-light Llama for mobile and embedded. Sub-2GB VRAM with Q4. 2BConsumer GPUMac / Apple SiliconQ4 K M2.1 GB+3.8%perplexity rise https://quantized.uk/quant-hub/gemma-2-2b/ Gemma 2 2B Instruct Google Gemma 2 Ultra-compact Gemma 2. Runs on 4GB VRAM; great for edge prototyping. Running BotPsy 0.8B locally At Q4 K M and 4K of context, BotPsy 0.8B needs about 0.6 GB — 0.5 GB of weights, 0.05 GB of KV cache and a 0.1 GB activation buffer. The smallest cards in this index that clear that comfortably are 8 GB ones — 11 of them, from the Mac M1 8G up — and 78 of the 78 cards here do. These are calculated figures, not measurements: the estimate stops counting a card as comfortable at 88% of its VRAM, which is roughly the room a desktop session needs. What longer context costs Going from 4K to 32K adds about 0.33 GB, taking the total to 1.0 GB. That is gentler than the parameter count suggests: only 6 of 24 layers keep a KV cache that grows with context, so the cache scales at a fraction of the usual rate. The model's native window is 256K; holding all of it at Q4 K M would need about 4 GB. Which build to download This index only tracks BotPsy 0.8B in GGUF, across 2 levels Q4 K M, Q8 0 . No per-level perplexity sweep has been published for this model, so the quality column is empty rather than estimated — within one model, more bits per weight is the only ordering the data supports. No throughput has been measured for this model on this site's hardware. GGUF runs on llama.cpp and Ollama across NVIDIA, AMD and Apple silicon; AWQ and GPTQ target vLLM on CUDA and ROCm; EXL2 is ExLlamaV2 — CUDA only, and now archived, so local use rather than serving. Common questions - How much VRAM does BotPsy 0.8B need? - About 0.6 GB at Q4 K M with 4K of context and batch 1, rising to roughly 1.0 GB at 32K. That figure is weights plus KV cache plus a 10% activation buffer, calculated from the model's architecture rather than measured on a card. - Will BotPsy 0.8B run on a 8GB GPU? - Yes — at Q4 K M and 4K context it needs about 0.6 GB, which leaves 5.4 GB spare on a Mac M1 8G, or on any of the other 8 GB cards here 11 in all . That is the smallest size in this index that clears it comfortably; 78 of 78 do. - Which quantization of BotPsy 0.8B should I use? - No published quality comparison exists for this model, so pick by footprint: Q4 K M is the level most people run, and a higher bits-per-weight level is more faithful. All 2 levels in the index are Q4 K M, Q8 0. Where this model fits Sized at Q4 K M with a 4K context window, smallest card first. Comfortable means the estimate uses at most 88% of the memory. - Runs comfortably on - Mac M1 8G8GB · +5.4 https://quantized.uk/gpu/mac-m1-8g/ Mac M3 8G8GB · +5.4 https://quantized.uk/gpu/mac-m3-8g/ RTX 40608GB · +7.4 https://quantized.uk/gpu/rtx-4060/ RTX 4060 Ti 8G8GB · +7.4 https://quantized.uk/gpu/rtx-4060-ti-8g/ Radeon RX 9060 XT 8G8GB · +7.4 https://quantized.uk/gpu/radeon-rx-9060-xt-8g/ - Ships in - GGUF https://quantized.uk/formats/gguf/ - Try it yourself - Size it in the calculator https://quantized.uk/tools/vram-calc/?model=botpsy-0-8b&quant=Q4 K M Generate the run command https://quantized.uk/tools/cli-gen/?model=botpsy-0-8b&quant=Q4 K M How to actually run this Deployment guides for this model and this class of hardware. This page's figures change when the model or the runtime does.Last updated 2026-11-17 RSS → /feed.xml https://quantized.uk/feed.xml