FitMyLLM
TII/Dense

TIIFalcon-H1 7B

Flagship hybrid 7B. Outperforms models 7x its size on reasoning.

chatcodingreasoning
7.59B
Parameters
256K
Context length
10
Benchmarks
6
Quantizations
Architecture
Dense
Released
2025-08-01
Layers
44
KV Heads
2
Head Dim
128
Family
falcon

Quantization Options

Context length:
QuantBitsVRAM @ 16KQuality
Q4_K_M4.89
5.6 GB
5.1 + 0.5 KV
good
Q5_K_S5.57
6.3 GB
5.8 + 0.5 KV
good
Q5_K_M5.7
6.4 GB
5.9 + 0.5 KV
good
Q6_K6.56
7.2 GB
6.7 + 0.5 KV
excellent
Q8_08.5
9.1 GB
8.6 + 0.5 KV
lossless
FP1616
16.2 GB
15.7 + 0.5 KV
lossless

Select your GPU above to see speed estimates and compatibility for each quantization.

Deploying for a team or in production? Size GPUs, cost & scaling in Enterprise →
Ready to run this?Rent by the hour

Rent a GPU and run Falcon-H1 7B now

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (10)

Run this model

Easiest way to get started·Beginners
Docs ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run falcon:7b

Ollama's default build of this model. For Q4_K_M specifically, pick a tag from ollama.com/library/falcon/tags.

Setup guide
>_

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more
Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

NVIDIA Tesla C2070
6 GB VRAM • 143 GB/s
NVIDIA
NVIDIA Tesla C2075
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla C2090
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla M2070
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla M2070-Q
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla M2075
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla M2090
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla X2070
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla X2090
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla K20X
6 GB VRAM • 250 GB/s
NVIDIA
NVIDIA Tesla K20Xm
6 GB VRAM • 250 GB/s
NVIDIA

Find the best GPU for Falcon-H1 7B

Build Hardware for Falcon-H1 7B
Spec sheet

Falcon-H1 7B — 7.59B Dense.

Specifications
Parameters
7.59B
Architecture
Dense Transformer
Context Length
256K tokens
Capabilities
chat, coding, reasoning
Release Date
2025-08-01
Provider
TII
Family
falcon
VRAM requirements
QuantBPWVRAMQuality
Q4_K_M4.895.1 GB94%
Q5_K_S5.575.8 GB96%
Q5_K_M5.75.9 GB96%
Q6_K6.566.7 GB97%
Q8_08.58.6 GB100%
FP161615.7 GB100%
Benchmark scores
HumanEval86.6
MMLU-PRO51.8
MATH73.4
IFEval85.3
BBH62.3
GPQA8.1
MUSR21.2
MBPP80.7
AIME14.0
GPQA Diamond56.9
Run command

Run Falcon-H1 7B locally with Ollama — needs 5.1 GB VRAM at Q4_K_M:

$ollama run falcon:7b
Compatible GPUs
30 @ Q4_K_M