Tiny BloomForCausalLM — Hardware Requirements & GPU Compatibility
Chat
Tiny BloomForCausalLM is a 2M-parameter open language model from trl-internal-testing in the Orca family. At Q4_K_M it needs about 0.01 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 · 32K)Best on 24 GB (Q4_K_M · ~65520 tok/s · 32K)Macs from 32 GB (~8400 tok/s)
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Tiny BloomForCausalLM
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve trl-internal-testing/tiny-BloomForCausalLM --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 (11 GB headroom) · Q4_K_M
- Generation speed
- ~23400 tok/s
- generation speed
- Cost per 1M output tokens
- <$0.001
- per 1M output tokens
How Much VRAM Does Tiny BloomForCausalLM Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 0.0 GB | 0.6 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 32K context · ~65520 tok/s | |
| 0.0 GB | 0.6 GB | 3-bit medium — 3-bit medium quantization | Fits: 32K context · ~65520 tok/s | |
| 0.0 GB | 0.6 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 32K context · ~65520 tok/s | |
| 0.0 GB | 0.6 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 32K context · ~65520 tok/s | |
| 0.0 GB | 0.6 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 32K context · ~65520 tok/s | |
| 0.0 GB | 0.6 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 32K context · ~65520 tok/s | |
| 0.0 GB | 0.6 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 32K context · ~65520 tok/s |
Selected Q4_K_M
4-bit medium quantization0.3GBat 16K context
- Weights
- 0.1 GB
- KV cache
- 0.0 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 23.7 GB free · ~65520 tok/s
≥50 tok/s needs ≥1 GB/s · RTX 5090 ~116480, RTX 3090 Ti ~65520
Which Hardware Can Run Tiny BloomForCausalLM?
Q4_K_M · 0.0 GBTiny BloomForCausalLM (Q4_K_M) requires 0.0 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1+ GB is recommended. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 176 devices with unified memory can run Tiny BloomForCausalLM, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
≤ 11 GB
≤ 11 GB tier →fits · 7.7 GB free · up to 32K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~49420Simulate output on RTX 3080RTX 2080 Ti~40040Simulate output on RTX 2080 TiRTX 3070 Ti~39540Simulate output on RTX 3070 TiM3*8 GB~7168Simulate output on iMac 24" M3 (8 GB)Orin Nano~6630Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~4774Simulate output on iPhone 1720 GB
fits · 19.7 GB free · up to 32K ctx
1 GPU
RX 7900 XT~48000Simulate output on RX 7900 XT32–40 GB
fits · 31.7 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~116480Simulate output on RTX 5090M5 Max36 GB~32200Simulate output on Mac Studio M5 Max (36 GB)M532 GB~10752Simulate output on MacBook Air 13" M5 (32 GB)Orin~13312Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~8775Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Tiny BloomForCausalLM
Orca family · 9 models →Specifications
- Publisher
- trl-internal-testing
- Family
- Orca
- Parameters
- 2M
- Architecture
- BloomForCausalLM
- Vocabulary Size
- 250,680
- Release Date
- 2024-11-25
Frequently Asked Questions
How much VRAM does Tiny BloomForCausalLM need?
Tiny BloomForCausalLM requires 0.0 GB of VRAM at Q4_K_M, or 0.0 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 2M × 4.8 bits ÷ 8 = 0 GB
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
VRAM usage by quantization
What's the best quantization for Tiny BloomForCausalLM?
For Tiny BloomForCausalLM, Q4_K_M (0.0 GB) offers the best balance of quality and VRAM usage. Q5_K_M (0.0 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 0.0 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Tiny BloomForCausalLM on a Mac?
Yes — Mac Mini M1 (8 GB) and 155 other Macs can run Tiny BloomForCausalLM. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 0.0 GB of usable unified memory (RAM minus macOS overhead).
Can I run Tiny BloomForCausalLM locally?
Yes — Tiny BloomForCausalLM can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Tiny BloomForCausalLM?
At Q4_K_M, Tiny BloomForCausalLM can reach ~480000 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~65520 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 ÷ 0.01 × 0.65 = ~520000 tok/s
Estimated speed at Q4_K_M (0.0 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Tiny BloomForCausalLM?
At Q4_K_M, the download is about 0.01 GB. The full-precision BF16 version is 0.01 GB. The smallest option (Q2_K) is 0.01 GB.
Which GPUs can run Tiny BloomForCausalLM?
52 consumer GPUs can run Tiny BloomForCausalLM at Q4_K_M. 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 Tiny BloomForCausalLM?
176 devices with unified memory can run Tiny BloomForCausalLM at Q4_K_M (0.0 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Apple iPhone 17 Pro, Asus ROG Flow Z13 (2025, 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.