Skip to content
Model Pareto

Falcon-H1-34B-Instruct

TII (Falcon)Open weightshuggingface.co ↗
Compare with nearest rivalsCompare with…
Input
—
Output
—
Speed
~83tok/sest.
Context
262Ktokens

Hybrid attention + Mamba-2, largest Falcon-H1 size. No API price found. Falcon-H1R-7B (reasoning) is tracked separately.

Rankings

Self-hostingEstimated

How we estimate →

What it would cost to run these open weights yourself on rented GPUs. No API sells this model, so this is its price on the chart.

Hardware
1× B200 180GB
FP8 weights
Throughput
~4,722 tok/s
many requests batched
Price
$0.17–1.52 /M tok
busy → light use
On your own machine
RTX 5090 32GB (int4, ~75 tok/s single-stream)
single consumer GPU or Mac
Assumptions (5)
  • FP8 weights (33.6B params) + 25% KV-cache headroom ≈ 42 GB
  • 1× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
  • ~4,722 output tok/s aggregate at batch 135 (bandwidth-bound)
  • Blended 3:1 input:output; prefill ~31,641 tok/s
  • Low = 75% utilization at the low GPU price; high = 20% at the high price

Benchmark scores

~ italic, dashed = no published score yet, estimated from related benchmarks.

Coding

DeepSWE v1.1Estimated
~#29 of 31 (estimated)~39.4%
  1. #1DeepSeek V4.1 Flash74.2%
  2. #2Grok 4.772.6%
  3. #28Qwen3.8 27B42.2%
  4. ~#29Falcon-H1-34B-InstructEstimated39.4%
  5. #29Nex-N2.5-Mini36.1%
No published score — estimated from related benchmarks
Terminal-Bench 4.0Estimated
~#39 of 84 (estimated)~0.6%
  1. #1Claude Sonnet 5.563.6%
  2. #2Claude Opus 5.559.6%
  3. #32Qwen3.7 Plus1.0%
  4. ~#39Falcon-H1-34B-InstructEstimated0.6%
  5. #39Command A+0.5%
No published score — estimated from related benchmarks
AA Coding Agent IndexEstimated
~last of 15 (estimated)below measured range (<41.1)
  1. #1Claude Opus 5.566.0
  2. #2Claude Fable 5.162.2
  3. #14GPT-6 Luna41.1
  4. ~#15Falcon-H1-34B-InstructEstimated<41.1
No published score — estimated from related benchmarks

Hard reasoning