Parable Granite 4.1 8B Claude Fable 5 — Hardware Requirements & GPU Compatibility
ChatReasoning
Parable Granite 4.1 8B Claude Fable 5 is a 8.4B-parameter open language model from AnkitAI in the Granite family. It supports a context window of up to 131,072 tokens. At Q4_K_M it needs about 5.66 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 8K)Best on 24 GB (Q4_K_M · ~116 tok/s · 64K)Macs from 16 GB (Q4_K_M · ~25 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Parable Granite 4.1 8B Claude Fable 5
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve AnkitAI/Parable-Granite-4.1-8B-Claude-Fable-5 --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 (4 GB headroom) · Q4_K_M
- Generation speed
- ~41 tok/s
- generation speed
- Cost per 1M output tokens
- $0.46
- per 1M output tokens
How Much VRAM Does Parable Granite 4.1 8B Claude Fable 5 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 4.2 GB | 9.2 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 64K context · ~156 tok/s | |
| 4.7 GB | 9.8 GB | 3-bit medium — 3-bit medium quantization | Fits: 64K context · ~139 tok/s | |
| 5.7 GB | 10.7 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 64K context · ~116 tok/s | |
| 6.6 GB | 11.6 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 64K context · ~99 tok/s | |
| 7.5 GB | 12.6 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 64K context · ~87 tok/s | |
| 9.0 GB | 14.1 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 64K context · ~73 tok/s | |
| 17.4 GB | 22.4 GB | 16-bit · full — Full half-precision — baseline for inference | Fits: 32K context · ~38 tok/s |
Selected Q4_K_M
4-bit medium quantization8.0GBat 16K context
- Weights
- 5.0 GB
- KV cache
- 2.7 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 16.0 GB free · ~116 tok/s
≥50 tok/s needs ≥435 GB/s · RTX 5090 ~206, RTX 3090 Ti ~116
Which Hardware Can Run Parable Granite 4.1 8B Claude Fable 5?
Q4_K_M · 5.7 GBParable Granite 4.1 8B Claude Fable 5 (Q4_K_M) requires 5.7 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 8+ GB is recommended. Using the full 131K context window can add up to 21.1 GB, bringing total usage to 26.8 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3070 Ti. 151 devices with unified memory can run Parable Granite 4.1 8B Claude Fable 5, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), NVIDIA Jetson Orin Nano 8GB (Super).
12 GB
12 GB tier →fits · 4.0 GB free · up to 32K ctx
10 GPUs · 1 device family
RTX 3080 Ti~105Simulate output on RTX 3080 TiRTX 5070~77Simulate output on RTX 5070RTX 4070~58Simulate output on RTX 4070iPhone~10Simulate output on Apple iPhone 17 Pro20 GB
fits · 12.0 GB free · up to 64K ctx
1 GPU
RX 7900 XT~85Simulate output on RX 7900 XT32–40 GB
fits · 24.0 GB free · up to 128K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~206Simulate output on RTX 5090M5 Max36 GB~57Simulate output on Mac Studio M5 Max (36 GB)M532 GB~19Simulate output on MacBook Air 13" M5 (32 GB)Orin~24Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~16Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Parable Granite 4.1 8B Claude Fable 5
Granite family · 26 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| ALoDLM 8BAmazon | — | 7.6 GB | ~119 | same size |
| Llm Jp 4.1 8B Thinkingllm-jp | — | 7.6 GB | ~115 | same size |
| Ling 3.0 TinyInclusion AI | — | 5.5 GB | ~364 | same size |
| Apertus V1.5 8Bswiss-ai | — | 8.5 GB | ~111 | same size |
| LFM2.5 8B A1BLiquid AI | — | 5.6 GB | ~335 | same size |
| BitCPM CANN 8BOpenBMB | — | 5.6 GB | ~127 | same size |
Specifications
- Publisher
- AnkitAI
- Family
- Granite
- Parameters
- 8.4B
- Architecture
- GraniteForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 100,352
- Release Date
- 2026-07-13
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Parable Granite 4.1 8B Claude Fable 5 need?
Parable Granite 4.1 8B Claude Fable 5 requires 5.7 GB of VRAM at Q4_K_M, or 17.4 GB at FP16. Full 131K context adds up to 21.1 GB (26.8 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 8.4B × 4.8 bits ÷ 8 = 5 GB
KV Cache + Overhead ≈ 0.7 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 ≈ 21.8 GB (at full 131K context)
VRAM usage by quantization
What's the best quantization for Parable Granite 4.1 8B Claude Fable 5?
For Parable Granite 4.1 8B Claude Fable 5, Q4_K_M (5.7 GB) offers the best balance of quality and VRAM usage. Q5_K_M (6.6 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 4.2 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Parable Granite 4.1 8B Claude Fable 5 on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run Parable Granite 4.1 8B Claude Fable 5. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 5.7 GB of usable unified memory (RAM minus macOS overhead).
Can I run Parable Granite 4.1 8B Claude Fable 5 locally?
Yes — Parable Granite 4.1 8B Claude Fable 5 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Parable Granite 4.1 8B Claude Fable 5?
At Q4_K_M, Parable Granite 4.1 8B Claude Fable 5 can reach ~848 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~116 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 ÷ 5.66 × 0.65 = ~919 tok/s
Estimated speed at Q4_K_M (5.7 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Parable Granite 4.1 8B Claude Fable 5?
At Q4_K_M, the download is about 5.03 GB. The full-precision FP16 version is 16.76 GB. The smallest option (Q2_K) is 3.56 GB.
Which GPUs can run Parable Granite 4.1 8B Claude Fable 5?
52 consumer GPUs can run Parable Granite 4.1 8B Claude Fable 5 at Q4_K_M. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 7600. 40 GPUs have plenty of headroom for comfortable inference.
Which devices can run Parable Granite 4.1 8B Claude Fable 5?
151 devices with unified memory can run Parable Granite 4.1 8B Claude Fable 5 at Q4_K_M (5.7 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.