HF Moshiko — Hardware Requirements & GPU Compatibility
Chat
HF Moshiko is a 7.8B-parameter open language model from kmhf. It supports a context window of up to 3,000 tokens. At BF16 it needs about 16.94 GB of VRAM — see which GPUs and Macs can run it below.
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run HF Moshiko
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
vllm serve kmhf/hf-moshiko --max-model-len 3000vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3090 (24 GB) (6 GB headroom) · BF16
- Generation speed
- ~36 tok/s
- generation speed
- Cost per 1M output tokens
- $1.53
- per 1M output tokens
How Much VRAM Does HF Moshiko Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 16.9 GB | — | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 3K context · ~39 tok/s |
Selected BF16
Brain floating point 1617.4GBat 3K context
- Weights
- 15.6 GB
- KV cache
- 1.6 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 6.6 GB free · ~39 tok/s
≥50 tok/s needs ≥1.30 TB/s · RTX 5090 ~69
Which Hardware Can Run HF Moshiko?
BF16 · 16.9 GBHF Moshiko (BF16) requires 16.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 23+ GB is recommended. Using the full 3K context window can add up to 0.5 GB, bringing total usage to 17.4 GB. 8 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 122 devices with unified memory can run HF Moshiko, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Mini M5 Pro (24 GB).
20 GB
fits · 2.6 GB free · up to 3K ctx
1 GPU
RX 7900 XT~28Simulate output on RX 7900 XT32–40 GB
fits · 14.6 GB free · up to 3K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~69Simulate output on RTX 5090M5 Max36 GB~19Simulate output on Mac Studio M5 Max (36 GB)M532 GB~6Simulate output on MacBook Air 13" M5 (32 GB)Orin~8Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~5Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at BF16
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Ling 3.0 TinyInclusion AI | — | 5.5 GB | ~364 | same size |
| BitCPM CANN 8BOpenBMB | — | 5.6 GB | ~127 | same size |
| Gemma 4 E4BGoogle | — | 5.6 GB | ~123 | same size |
| Olmo 3 7B InstructAllen AI | — | 8.4 GB | ~114 | same size |
| Phi Mini MoE InstructMicrosoft | — | 5.4 GB | ~239 | same size |
| Gemma 3n E4B ITGoogle | — | 7.7 GB | ~127 | same size |
Specifications
- Publisher
- kmhf
- Parameters
- 7.8B
- Architecture
- MoshiForConditionalGeneration
- Context Length
- 3,000 tokens
- Vocabulary Size
- 32,000
- Release Date
- 2024-09-27
Frequently Asked Questions
How much VRAM does HF Moshiko need?
HF Moshiko requires 16.9 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 7.8B × 16 bits ÷ 8 = 15.6 GB
KV Cache + Overhead ≈ 1.3 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 ≈ 1.8 GB (at full 3K context)
VRAM usage by quantization
Can I run HF Moshiko on a Mac?
Yes — Mac Mini M5 Pro (24 GB) and 106 other Macs can run HF Moshiko. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 16.9 GB of usable unified memory (RAM minus macOS overhead).
Can I run HF Moshiko locally?
Yes — HF Moshiko can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is HF Moshiko?
At BF16, HF Moshiko can reach ~283 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~39 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 ÷ 16.94 × 0.65 = ~307 tok/s
Estimated speed at BF16 (16.9 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of HF Moshiko?
At BF16, the download is about 15.57 GB.
Which GPUs can run HF Moshiko?
8 consumer GPUs can run HF Moshiko at BF16. Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU has plenty of headroom for comfortable inference.
Which devices can run HF Moshiko?
122 devices with unified memory can run HF Moshiko at BF16 (16.9 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.