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.

⬇ 4.3K HF downloads♥ 22 likesqvac/BotPsy-0.8B-GGUFs· stats from 11/17/2026
Consumer GPUMac / Apple SiliconCPU / VPS

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

FormatLevelBPWVRAMPPL LossSpeedSourceActions
GGUFQ4_K_M5.6278773791501820.6 GB——Estimated
CalcHF
GGUFQ8_08.6321166103741010.9 GB——Estimated
CalcHF

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_Mqvac/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_0qvac/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 ↗

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.

Ships in
GGUF

This page's figures change when the model or the runtime does.Last updated 2026-11-17 RSS → /feed.xml