Josiefied Qwen3.5 0.8B Gabliterated V1 — Hardware Requirements & GPU Compatibility
Chat
Josiefied Qwen3.5 0.8B Gabliterated V1 is a 853M-parameter open language model from Goekdeniz-Guelmez in the Qwen 3.5 family. It supports a context window of up to 262,144 tokens. At BF16 it needs about 2.06 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (BF16 · 256K)Best on 24 GB (BF16 · ~318 tok/s · 256K)Macs from 8 GB (BF16 · ~35 tok/s)
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Josiefied Qwen3.5 0.8B Gabliterated V1
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve Goekdeniz-Guelmez/Josiefied-Qwen3.5-0.8B-gabliterated-v1 --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (9 GB headroom) · BF16
- Generation speed
- ~114 tok/s
- generation speed
- Cost per 1M output tokens
- $0.20
- per 1M output tokens
How Much VRAM Does Josiefied Qwen3.5 0.8B Gabliterated V1 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 2.1 GB | 2.2 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 256K context · ~318 tok/s |
Selected BF16
Brain floating point 162.1GBat 16K context
- Weights
- 1.7 GB
- KV cache
- 0.1 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 21.9 GB free · ~318 tok/s
≥50 tok/s needs ≥158 GB/s · RTX 5090 ~565, RTX 3090 Ti ~318
Which Hardware Can Run Josiefied Qwen3.5 0.8B Gabliterated V1?
BF16 · 2.1 GBJosiefied Qwen3.5 0.8B Gabliterated V1 (BF16) requires 2.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 3+ GB is recommended. Using the full 262K context window can add up to 1.6 GB, bringing total usage to 3.6 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Josiefied Qwen3.5 0.8B Gabliterated V1, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 5.9 GB free · up to 256K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~240Simulate output on RTX 3080RTX 2080 Ti~194Simulate output on RTX 2080 TiRTX 3070 Ti~192Simulate output on RTX 3070 TiM3*8 GB~35Simulate output on iMac 24" M3 (8 GB)Orin Nano~32Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~23Simulate output on iPhone 1720 GB
fits · 17.9 GB free · up to 256K ctx
1 GPU
RX 7900 XT~233Simulate output on RX 7900 XT32–40 GB
fits · 29.9 GB free · up to 256K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~565Simulate output on RTX 5090M5 Max36 GB~156Simulate output on Mac Studio M5 Max (36 GB)M532 GB~52Simulate output on MacBook Air 13" M5 (32 GB)Orin~65Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~43Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at BF16
Alternatives to Josiefied Qwen3.5 0.8B Gabliterated V1
Qwen 3.5 family · 34 models →Similar models
5| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Bitnet B1.58 2B 4TMicrosoft | — | 2.3 GB | ~303 | same size |
| Sarashina2.2 0.5B Instruct v0.1sbintuitions | — | 1.3 GB | ~728 | same size |
| Gpt2 LargeOpenAI | — | 0.5 GB | ~1213 | same size |
| OneReason 0.8B Pretrain CompetitionOpenOneRec | — | 1.7 GB | ~728 | same size |
| H2ovl Mississippi 800Mh2oai | — | 3.2 GB | ~360 | same size |
Specifications
- Publisher
- Goekdeniz-Guelmez
- Family
- Qwen 3.5
- Parameters
- 853M
- Architecture
- Qwen3_5ForConditionalGeneration
- Context Length
- 262,144 tokens
- Vocabulary Size
- 248,320
- Release Date
- 2026-03-09
Frequently Asked Questions
How much VRAM does Josiefied Qwen3.5 0.8B Gabliterated V1 need?
Josiefied Qwen3.5 0.8B Gabliterated V1 requires 2.1 GB of VRAM at BF16. Full 262K context adds up to 1.6 GB (3.6 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 853M × 16 bits ÷ 8 = 1.7 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 1.9 GB (at full 262K context)
VRAM usage by quantization
Can I run Josiefied Qwen3.5 0.8B Gabliterated V1 on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run Josiefied Qwen3.5 0.8B Gabliterated V1. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 2.1 GB of usable unified memory (RAM minus macOS overhead).
Can I run Josiefied Qwen3.5 0.8B Gabliterated V1 locally?
Yes — Josiefied Qwen3.5 0.8B Gabliterated V1 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Josiefied Qwen3.5 0.8B Gabliterated V1?
At BF16, Josiefied Qwen3.5 0.8B Gabliterated V1 can reach ~2330 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~318 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 2.06 × 0.65 = ~2524 tok/s
Estimated speed at BF16 (2.1 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Josiefied Qwen3.5 0.8B Gabliterated V1?
At BF16, the download is about 1.71 GB.
Which GPUs can run Josiefied Qwen3.5 0.8B Gabliterated V1?
52 consumer GPUs can run Josiefied Qwen3.5 0.8B Gabliterated V1 at BF16. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
Which devices can run Josiefied Qwen3.5 0.8B Gabliterated V1?
163 devices with unified memory can run Josiefied Qwen3.5 0.8B Gabliterated V1 at BF16 (2.1 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.